New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Detecting Data And Model Poisoning

by mukul975 in mukul975/Anthropic-Cybersecurity-Skills

Identify poisoned training data and backdoored ML models across the pipeline using IBM's Adversarial Robustness Toolbox (activation clustering, spectral signatures, trigger reconstruction), Cleanlab…

Apache-2.0Auto-check passedSecurity

Install Detecting Data And Model Poisoning

skills CLI
$ npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill detecting-data-and-model-poisoning -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills detecting-data-and-model-poisoning --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/detecting-data-and-model-poisoning .claude/skills/detecting-data-and-model-poisoning && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
detecting-data-and-model-poisoning
GitHub stars
34k
Token cost
~2.7k tokens
SKILL.md length
763 words
Files
5 (incl. scripts, references)
Skills in repo
644
Repo updated
First seen
Licence
Apache-2.0

At a glance

Identify poisoned training data and backdoored ML models across the pipeline using IBM's Adversarial Robustness Toolbox (activation clustering, spectral signatures, trigger reconstruction), Cleanlab…

  • Works in 6 steps: Verify data and model provenance/integrity → Detect label/data-quality issues with… → Detect poisoned samples via ART… → …
  • Reconstruction)
  • SKILL.md covers Overview, When to Use, Prerequisites and Objectives, plus 5 more sections
  • Runs Python scripts from its folder; calls pip and python

What it does

Detecting Data And Model Poisoning is an agent skill from mukul975/Anthropic-Cybersecurity-Skills. Identify poisoned training data and backdoored ML models across the pipeline using IBM's Adversarial Robustness Toolbox (activation clustering, spectral signatures, trigger reconstruction), Cleanlab for label-quality issues, and supply-chain checks like weight-hash verification and safetensors enforcement. Use before training or deploying on third-party/user-contributed data or downloaded checkpoints, during ML supply-chain reviews, or when investigating model misbehavior tied to specific inputs (suspected…

Its SKILL.md is about 2.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts and reference files (for example `references/api-reference.md`, `references/standards.md` and `scripts/agent.py`).

It sits in Security, covering Supply chain security, Machine learning and Data cleaning. The repository describes itself as: 817 structured cybersecurity skills for AI agents · Mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF & MITRE F3 (Fight Fraud) · agentskills.io…. The licence is Apache-2.0.

When your agent uses it

  • Reconstruction)
  • Cleanlab for label-quality issues
  • Supply-chain checks like weight-hash verification and safetensors enforcement

Example prompts

  • “/detecting-data-and-model-poisoning”

Requirements

  • Python 3

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Verify data and model provenance/integrity
  2. Detect label/data-quality issues with Cleanlab
  3. Detect poisoned samples via ART activation clustering
  4. Confirm with ART spectral signatures
  5. Probe the model for backdoor triggers
  6. Quarantine, retrain, and report

What it can do on your machine

Read from SKILL.md and the folder at commit 54a7988. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • pip
    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • github.com
    • genai.owasp.org
    • atlas.mitre.org

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Detecting Data And Model Poisoning loads about 2.7k tokens when it runs, and up to ~3.7k if it reads all its reference files. Until then it costs about 141 tokens; SKILL.md has 763 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~141
When it runs · the whole SKILL.md, loaded when a task matches
~2.7k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from mukul975/Anthropic-Cybersecurity-Skills at commit 54a7988, republished under its Apache-2.0 licence (© mukul975). 763 words, ~2,737 tokens.

Download SKILL.mdSave it as .claude/skills/detecting-data-and-model-poisoning/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
detecting-data-and-model-poisoning
description
Identify poisoned training data and backdoored ML models across the pipeline using IBM's Adversarial Robustness Toolbox (activation clustering, spectral signatures, trigger reconstruction), Cleanlab for label-quality issues, and supply-chain checks like weight-hash verification and safetensors enforcement. Use before training or deploying on third-party/user-contributed data or downloaded checkpoints, during ML supply-chain reviews, or when investigating model misbehavior tied to specific inputs (suspected backdoor trigger).
domain
cybersecurity
subdomain
ai-security
tags
ai-security, data-poisoning, model-backdoor, ml-supply-chain, adversarial-robustness-toolbox, activation-clustering, spectral-signatures, model-integrity
version
1.0
author
mahipal
license
Apache-2.0
nist_ai_rmf
MEASURE-2.7
atlas_techniques
AML.T0020, AML.T0018

Detecting Data and Model Poisoning

Authorized-use-only notice: This skill includes routines that craft poisoned samples and backdoor triggers for defensive validation. Generate and use poisoned data and backdoored models only in isolated test environments you control. Never deploy a backdoored model or distribute poisoned datasets.

Overview

Data poisoning and model backdooring attack the integrity of an ML system at training time rather than at inference. In data poisoning (MITRE ATLAS AML.T0020 Poison Training Data), an adversary injects manipulated samples into the training, fine-tuning, or RAG corpus so the resulting model misbehaves — degraded accuracy, targeted misclassification, or an attacker-chosen bias. In model backdooring (MITRE ATLAS AML.T0018 Backdoor ML Model), the model behaves normally on clean inputs but produces an attacker-chosen output whenever a hidden trigger (a pixel patch, a rare token, a phrase) is present. Both are amplified by ML supply-chain compromise (AML.T0010): poisoned public datasets, trojaned pre-trained weights downloaded from a hub, or a malicious model serialization. This is OWASP LLM04:2025 Data and Model Poisoning.

Detection spans the pipeline. On the data side: provenance and integrity checks, statistical outlier and label-flip detection, and de-duplication of suspiciously near-identical samples. On the model side: activation-clustering and spectral-signature analysis (which exploit the fact that poisoned samples activate the network differently than clean ones) and trigger reconstruction. On the supply-chain side: verifying weights hashes/signatures and refusing unsafe serialization formats (pickle-based .bin/.pt) in favor of safetensors. This skill implements all three using IBM's Adversarial Robustness Toolbox (ART), Cleanlab for label-quality issues, and integrity tooling.

When to Use

  • Before training/fine-tuning on third-party or user-contributed data.
  • Before deploying a model built on a downloaded pre-trained checkpoint.
  • During an ML supply-chain security review.
  • When investigating anomalous model behavior tied to specific inputs (possible backdoor trigger).
  • As a CI/CD gate that scans datasets and model artifacts before they enter the pipeline.

Prerequisites

  • Python 3.10+ and a virtual environment.
  • Install the tooling:
bash
python -m venv .venv && source .venv/bin/activate

# IBM Adversarial Robustness Toolbox — poisoning detection defenses
pip install adversarial-robustness-toolbox

# Cleanlab — label/data quality issue detection
pip install cleanlab

# Modeling + safe serialization + hashing
pip install numpy scikit-learn safetensors

# (Choose one framework backend ART can wrap)
pip install tensorflow   # or: pip install torch

Objectives

  • Verify dataset and model-weight provenance and integrity (hashes/signatures, safe formats).
  • Detect label-quality issues and outliers in training data with Cleanlab.
  • Detect poisoned samples in a trained model using ART activation clustering.
  • Confirm findings with ART spectral-signature analysis.
  • Probe a suspect model for backdoor triggers and quantify trigger-induced misclassification.
  • Produce a poisoning-assessment report mapped to ATLAS AML.T0020 / AML.T0018.

MITRE ATT&CK Mapping

IDOfficial NameRelevance
AML.T0020Poison Training DataInjection of manipulated samples into the training corpus
AML.T0018Backdoor ML ModelTrigger-activated hidden behavior in the trained model
AML.T0010ML Supply Chain CompromisePoisoned public datasets / trojaned downloaded weights
AML.T0024Exfiltration via ML Inference APISome poisoning aims to leak data via the model's responses

Workflow

1. Verify data and model provenance/integrity

Refuse artifacts whose hash/signature you cannot verify, and prefer safetensors over pickle-based formats (pickle can execute code on load).

bash
# Verify a downloaded checkpoint against a published SHA-256
sha256sum model.safetensors
# compare to the hub-published digest

# Flag unsafe pickle-based weights in a directory
find ./models -type f \( -name "*.bin" -o -name "*.pt" -o -name "*.pkl" -o -name "*.ckpt" \)
python
# safe_load.py — load weights without executing pickle
from safetensors.numpy import load_file
weights = load_file("model.safetensors")   # no arbitrary code execution
Show full SKILL.md (310 more words)Show less
2. Detect label/data-quality issues with Cleanlab

Cleanlab finds mislabeled, outlier, and near-duplicate samples — common signatures of label-flip poisoning.

python
# cleanlab_scan.py
import numpy as np
from cleanlab.filter import find_label_issues

# pred_probs: out-of-sample predicted probabilities (n_samples x n_classes)
# labels: given integer labels (n_samples,)
def scan(labels: np.ndarray, pred_probs: np.ndarray):
    issues = find_label_issues(
        labels=labels, pred_probs=pred_probs,
        return_indices_ranked_by="self_confidence",
    )
    print(f"[*] {len(issues)} suspected label issues (potential poisoning)")
    return issues
3. Detect poisoned samples via ART activation clustering

ActivationDefence clusters per-class activations; a class whose activations split into two distinct clusters indicates injected (poisoned) samples.

python
# activation_defence.py
import numpy as np
from art.estimators.classification import KerasClassifier
from art.defences.detector.poison import ActivationDefence

def detect(model, x_train, y_train):
    classifier = KerasClassifier(model=model)          # wrap your trained model
    defence = ActivationDefence(classifier, x_train, y_train)
    report, is_clean_lst = defence.detect_poison(
        nb_clusters=2, nb_dims=10, reduce="PCA"
    )
    # is_clean_lst[i] == 0 marks a suspected poisoned sample
    poisoned_idx = np.where(np.array(is_clean_lst) == 0)[0]
    print(f"[*] activation clustering flagged {len(poisoned_idx)} samples")
    return poisoned_idx, report
4. Confirm with ART spectral signatures

Spectral signatures use the covariance spectrum of feature representations to surface poisoned samples — a strong second signal.

python
# spectral.py
import numpy as np
from art.estimators.classification import KerasClassifier
from art.defences.detector.poison import SpectralSignatureDefense

def detect(model, x_train, y_train, nb_classes):
    classifier = KerasClassifier(model=model)
    defence = SpectralSignatureDefense(
        classifier, x_train, y_train,
        expected_pp_poison=0.05, batch_size=128, eps_multiplier=1.5,
    )
    report, is_clean_lst = defence.detect_poison()
    poisoned_idx = np.where(np.array(is_clean_lst) == 0)[0]
    print(f"[*] spectral signatures flagged {len(poisoned_idx)} samples")
    return poisoned_idx, report
5. Probe the model for backdoor triggers

Test whether a candidate trigger flips predictions to an attacker target class far above the clean baseline.

python
# trigger_probe.py
import numpy as np

def test_trigger(model, x_clean, target_class, apply_trigger):
    """apply_trigger(x) stamps a candidate trigger (e.g. a corner pixel patch)."""
    clean_preds = model.predict(x_clean).argmax(axis=1)
    x_trig = np.stack([apply_trigger(x.copy()) for x in x_clean])
    trig_preds = model.predict(x_trig).argmax(axis=1)
    asr = float(np.mean(trig_preds == target_class))   # attack success rate
    base = float(np.mean(clean_preds == target_class))
    print(f"[*] target-class rate clean={base:.3f} triggered={asr:.3f}")
    return {"baseline": base, "trigger_success_rate": asr,
            "backdoor_suspected": asr - base > 0.5}
6. Quarantine, retrain, and report

Remove flagged samples (intersection of Cleanlab + ART signals is highest-confidence), retrain on the cleaned set, and re-test for the trigger. Document: artifact provenance, samples flagged by each method, trigger ASR before/after, and ATLAS mapping. Recommend dataset provenance controls, signed weights (safetensors + sigstore/cosign), and ongoing pipeline scanning.

Tools and Resources

ToolPurposeSource
Adversarial Robustness ToolboxActivation clustering & spectral-signature poisoning defenseshttps://github.com/Trusted-AI/adversarial-robustness-toolbox
CleanlabLabel/data-quality issue detectionhttps://github.com/cleanlab/cleanlab
safetensorsSafe (non-pickle) weight serializationhttps://github.com/huggingface/safetensors
OWASP LLM04:2025Data and Model Poisoning referencehttps://genai.owasp.org/llmrisk/llm042025-data-and-model-poisoning/
MITRE ATLASAI threat technique taxonomyhttps://atlas.mitre.org/

Detection Method Reference

LayerMethodToolSignal
Supply chainHash/signature + safe formatsha256/safetensorsTampered or unsafe artifact
DataLabel issues / outliersCleanlabMislabeled / injected samples
ModelActivation clusteringART ActivationDefencePer-class activation split
ModelSpectral signaturesART SpectralSignatureDefenseOutlier covariance spectrum
ModelTrigger probingcustomHigh trigger attack-success-rate

Validation Criteria

  • Dataset and weight provenance/integrity verified (hashes, safe format)
  • Unsafe pickle-based artifacts identified and avoided
  • Cleanlab label-issue scan run and suspicious samples listed
  • ART activation clustering executed with flagged sample indices
  • ART spectral-signature analysis run as confirmation
  • Backdoor trigger probe quantifies attack-success-rate vs. baseline
  • Highest-confidence poisoned samples quarantined (multi-method overlap)
  • Model retrained on cleaned data and re-tested for the trigger
  • Findings mapped to MITRE ATLAS AML.T0020 / AML.T0018 and OWASP LLM04:2025
  • Report delivered with remediation (provenance, signed weights, pipeline scanning)

© mukul975, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (scripts, references) in skills/detecting-data-and-model-poisoning of mukul975/Anthropic-Cybersecurity-Skills.

  • SKILL.md
  • LICENSE
  • references/api-reference.md
  • references/standards.md
  • scripts/agent.py

Open the folder on GitHubat commit 54a7988

Compare with similar skills

Detecting Data And Model Poisoning next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Detecting Data And Model Poisoning compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Detecting Data And Model Poisoning this skillmukul975/Anthropic-Cybersecurity-Skills34k—~2.7kAutomated safety check: PassApache-2.0
Sap Hana Cloud Data Intelligencesecondsky/sap-skills462—~3.2kAutomated safety check: PassGPL-3.0
Rf Model Importance Analysisaipoch/medical-research-skills1.9k—~2.7kAutomated safety check: PassMIT
Splitting Datasetsjeremylongshore/tons-of-skills-marketplace2.8k—~836Automated safety check: PassMIT
Scientific Data Preprocessingforyourhealth111-pixel/Vibe-Skills3.6k—~5kAutomated safety check: PassApache-2.0
ML Data Leakage Guardforyourhealth111-pixel/Vibe-Skills3.6k—~3.4kAutomated safety check: PassApache-2.0

Similar skills

  • Sap Hana Cloud Data Intelligence

    secondsky/sap-skills

    Develops data processing pipelines, integrations, and machine learning scenarios in SAP Data Intelligence Cloud.

    462 GitHub stars~3.2k tokensUpdated 5 days ago
    Data & AnalyticsAuto-check passed

  • Rf Model Importance Analysis

    aipoch/medical-research-skills

    A skill your agent uses when you need a standardized R CLI workflow to train a two-class random forest model from an expression-like feature matrix, rank variable importance, and generate…

    1.9k GitHub stars~2.7k tokensUpdated 23 days ago
    Data & AnalyticsAuto-check passed

  • Splitting Datasets

    jeremylongshore/tons-of-skills-marketplace

    Process split datasets into training, validation, and testing sets for ML model development.

    2.8k GitHub stars~836 tokensUpdated today
    Data & AnalyticsAuto-check passed

  • Scientific Data Preprocessing

    foryourhealth111-pixel/Vibe-Skills

    ⚠️ CRITICAL USER EXPERIENCE-BASED SKILL - ALWAYS CONSULT BEFORE DATA PREPROCESSING ⚠️ Prevents catastrophic errors (88.9% error rate in V1.0 case study) through multi-level feature analysis, data…

    3.6k GitHub stars~5k tokensUpdated 1 mo ago
    Data & AnalyticsAuto-check passed

  • ML Data Leakage Guard

    foryourhealth111-pixel/Vibe-Skills

    Detects and prevents data leakage in machine learning and mathematical modeling.

    3.6k GitHub stars~3.4k tokensUpdated 1 mo ago
    Data & AnalyticsAuto-check passed

  • Data Clean

    brycewang-stanford/Auto-Empirical-Research-Skills

    Produce documented data cleaning scripts that log every transformation with N before/after each step, generate a CONSORT-style exclusion flow diagram, create decision log entries for every…

    4.6k GitHub stars~1.1k tokensUpdated 5 days ago
    Data & AnalyticsAuto-check passed

More from mukul975/Anthropic-Cybersecurity-Skills

All 644 skills in this repo

  • Campaign Attribution Evidence Analysis

    mukul975/Anthropic-Cybersecurity-Skills

    Weighs infrastructure, TTP, malware code and timing evidence with the Diamond Model and competing hypotheses to reach a confidence-rated attribution.

    34k GitHub stars~2.3k tokensUpdated 1 mo ago
    Auto-check passed

  • Go Malware Analysis in Ghidra

    mukul975/Anthropic-Cybersecurity-Skills

    Walks through reverse engineering Go-compiled malware in Ghidra: parsing buildinfo and pclntab, recovering stripped function names and extracting dependencies.

    34k GitHub stars~2.8k tokensUpdated 1 mo ago
    Auto-check passed

  • LNK and Jump List Forensics

    mukul975/Anthropic-Cybersecurity-Skills

    Guides forensic analysis of Windows LNK shortcut files and Jump Lists with LECmd, JLECmd and manual parsing to show file access and program execution.

    34k GitHub stars~2.8k tokensUpdated 1 mo ago
    Auto-check passed

  • Malware Persistence Analysis with Autoruns

    mukul975/Anthropic-Cybersecurity-Skills

    Hunts Windows malware persistence with Sysinternals Autoruns, covering run keys, services, scheduled tasks and drivers, with baseline comparison.

    34k GitHub stars~1.2k tokensUpdated 1 mo ago
    Auto-check passed

  • NTFS MFT Deleted File Recovery

    mukul975/Anthropic-Cybersecurity-Skills

    Guides a Windows forensic examination of the NTFS Master File Table to recover deleted-file evidence, build timelines and spot timestomping.

    34k GitHub stars~2.7k tokensUpdated 1 mo ago
    Auto-check passed

  • Network Covert Channel Analysis

    mukul975/Anthropic-Cybersecurity-Skills

    Detects DNS tunneling, ICMP exfiltration and HTTP-based covert channels in packet captures and DNS logs when hunting for hidden command-and-control traffic.

    34k GitHub stars~2k tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about Detecting Data And Model Poisoning

What does Detecting Data And Model Poisoning do?

Identify poisoned training data and backdoored ML models across the pipeline using IBM's Adversarial Robustness Toolbox (activation clustering, spectral signatures, trigger reconstruction), Cleanlab…. Detecting Data And Model Poisoning is an agent skill from mukul975/Anthropic-Cybersecurity-Skills. Identify poisoned training data and backdoored ML models across the pipeline using IBM's Adversarial Robustness Toolbox (activation clustering, spectral signatures, trigger reconstruction), Cleanlab for label-quality issues, and supply-chain checks like weight-hash verification and safetensors enforcement.

When should I use Detecting Data And Model Poisoning?

Detecting Data And Model Poisoning fits situations like: reconstruction); cleanlab for label-quality issues; supply-chain checks like weight-hash verification and safetensors enforcement.

How do I install Detecting Data And Model Poisoning in Claude Code?

Run `npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill detecting-data-and-model-poisoning -a claude-code`. Or copy the skill folder (skills/detecting-data-and-model-poisoning in mukul975/Anthropic-Cybersecurity-Skills) into .claude/skills/detecting-data-and-model-poisoning in your project. Claude Code loads it when a task matches its description.

How do I install Detecting Data And Model Poisoning in Codex?

Run `npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill detecting-data-and-model-poisoning -a codex`. Or copy the skill folder (skills/detecting-data-and-model-poisoning in mukul975/Anthropic-Cybersecurity-Skills) into .agents/skills/detecting-data-and-model-poisoning in your project. Codex loads it when a task matches its description.

Can I use Detecting Data And Model Poisoning in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill detecting-data-and-model-poisoning -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/detecting-data-and-model-poisoning, .gemini/skills/detecting-data-and-model-poisoning, .github/skills/detecting-data-and-model-poisoning and .opencode/skills/detecting-data-and-model-poisoning in your project.

What does Detecting Data And Model Poisoning need to run?

Going by SKILL.md and its folder, Detecting Data And Model Poisoning needs Python for the scripts in its folder and the command-line tools its instructions call (pip and python). Our summary lists: Python 3.

Does Detecting Data And Model Poisoning access the network?

SKILL.md names 3 domains. As links in the text: github.com, genai.owasp.org and atlas.mitre.org. This is read from the text; nothing was executed.

Is Detecting Data And Model Poisoning safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Detecting Data And Model Poisoning use?

Detecting Data And Model Poisoning is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Detecting Data And Model Poisoning use?

About 2.7k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 976 tokens, read only when the agent opens those files.

What are the alternatives to Detecting Data And Model Poisoning?

Skills that share tags, products or a category with Detecting Data And Model Poisoning: Sap Hana Cloud Data Intelligence (secondsky/sap-skills, 462 stars), Rf Model Importance Analysis (aipoch/medical-research-skills, 1.9k stars), Splitting Datasets (jeremylongshore/tons-of-skills-marketplace, 2.8k stars) and Scientific Data Preprocessing (foryourhealth111-pixel/Vibe-Skills, 3.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Detecting Data And Model Poisoning?

mukul975 (a GitHub user) maintains it in mukul975/Anthropic-Cybersecurity-Skills, which has 34,116 GitHub stars. The repository holds 644 skills in this directory. The repository was last updated on August 31, 2026.

Source: mukul975/Anthropic-Cybersecurity-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.