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

Audit Native Memory Safety

by cyberful in cyberful/cyberful

Audit C, C++, unsafe Rust, native extensions, parsers, codecs, FFI boundaries, and systems code for memory corruption and low-level exploitation risk.

AGPL-3.0Auto-check passedSecurity

Install Audit Native Memory Safety

skills CLI
$ npx skills add cyberful/cyberful --skill audit-native-memory-safety -a claude-code

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

GitHub CLI
$ gh skill install cyberful/cyberful audit-native-memory-safety --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/cyberful/cyberful.git skills-src && mkdir -p .claude/skills && cp -r skills-src/cyberful/builtin/skills/audit-native-memory-safety .claude/skills/audit-native-memory-safety && 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
audit-native-memory-safety
GitHub stars
135
Token cost
~829 tokens
SKILL.md length
289 words
Files
4 (incl. references)
Skills in repo
85
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Audit C, C++, unsafe Rust, native extensions, parsers, codecs, FFI boundaries, and systems code for memory corruption and low-level exploitation risk.

  • Buffer overflows
  • SKILL.md covers Map Untrusted Bytes to Memory…, Establish Proof Obligations, Review Ownership and State and Validate With Focused…, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Out-of-bounds access

What it does

Audit Native Memory Safety is an agent skill from cyberful/cyberful. Audit C, C++, unsafe Rust, native extensions, parsers, codecs, FFI boundaries, and systems code for memory corruption and low-level exploitation risk. Use for buffer overflows, out-of-bounds access, use-after-free, double free, integer overflow, format strings, uninitialized memory, type confusion, race-induced corruption, unsafe deserialization, binary parsing, compiler hardening, sanitizers, and fuzzing strategy.

Its SKILL.md is about 830 tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `agents/openai.yaml`, `references/memory-unsafe-catalog.md` and `references/native-toolchain-hardening.md`).

It sits in Security, covering Penetration testing and Fuzzing. It works with C++ and Rust. The repository describes itself as: Cyberful is an open-source AI Red Team for discovering, exploiting, verifying, and remediating vulnerabilities. The licence is AGPL-3.0.

When your agent uses it

  • Buffer overflows
  • Out-of-bounds access
  • Integer overflow
  • Uninitialized memory

Example prompts

  • “/audit-native-memory-safety”

What it can do on your machine

Read from SKILL.md and the folder at commit ec598a6. 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

    No scripts in the folder and no shell commands in SKILL.md.

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

  • Network

    No URLs in SKILL.md.

    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

Audit Native Memory Safety loads about 829 tokens when it runs, and up to ~2k if it reads all its reference files. Until then it costs about 111 tokens; SKILL.md has 289 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~111
When it runs · the whole SKILL.md, loaded when a task matches
~829
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from cyberful/cyberful at commit ec598a6, republished under its AGPL-3.0 licence (© cyberful). 289 words, ~829 tokens.

Download SKILL.mdSave it as .claude/skills/audit-native-memory-safety/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
audit-native-memory-safety
description
Audit C, C++, unsafe Rust, native extensions, parsers, codecs, FFI boundaries, and systems code for memory corruption and low-level exploitation risk. Use for buffer overflows, out-of-bounds access, use-after-free, double free, integer overflow, format strings, uninitialized memory, type confusion, race-induced corruption, unsafe deserialization, binary parsing, compiler hardening, sanitizers, and fuzzing strategy.
metadata.domain
code-security
metadata.subdomain
native-memory-safety
metadata.triggers
native memory safety audit, C or C++ security review, unsafe Rust audit, memory corruption analysis, FFI boundary review
metadata.tags
memory-corruption, C, C++, unsafe-rust, sanitizers, fuzzing

Audit Native Memory Safety

Map Untrusted Bytes to Memory Operations

Inventory network protocols, files, IPC, device input, shared memory, environment, plugins, foreign calls, and privileged configuration. Trace length, offset, count, stride, allocation size, ownership, lifetime, type, and synchronization from parse to use.

Prioritize parsers and state machines reachable before authentication, code running with elevated identity, complex binary formats, custom allocators, unsafe FFI, and operations where attacker-controlled arithmetic determines memory layout.

Read memory-unsafe-catalog.md for review patterns. Read native-toolchain-hardening.md for validation and mitigation.

Establish Proof Obligations

For each memory operation, prove:

  • the object is alive and uniquely or correctly shared;
  • offset and length arithmetic cannot wrap;
  • the complete range lies within the actual allocation;
  • source and destination overlap semantics are correct;
  • terminators and element sizes are included;
  • signedness and width conversions preserve bounds;
  • type, alignment, and initialization are valid;
  • concurrent mutation cannot invalidate the proof.

Do not treat a nearby bounds check as sufficient. Trace whether it dominates the operation and uses the same canonical values.

Review Ownership and State

Draw allocation, alias, transfer, callback, cancellation, error, and free transitions. Include exception or long-jump paths, reference cycles, weak references, async completion, reentrancy, and foreign ownership conventions.

Look for cleanup that runs twice, callbacks after teardown, container mutation invalidating pointers, and handles reused with stale type or generation.

Validate With Focused Instrumentation

Use compiler warnings, static analysis, sanitizers, fuzzing, differential parsers, assertions, and minimized reproducers. Select sanitizers and harnesses for the suspected property; broad random fuzzing without the right state, dictionary, or oracle leaves deep logic untouched.

Report Exploit-Relevant Conditions

State controlled field, arithmetic or lifetime failure, invalid memory operation, allocator and platform context, reachable state, mitigations present, and observed consequence. Separate crash-only evidence, disclosure, write primitive, control-flow influence, and likely exploitability.

© cyberful, AGPL-3.0. 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 3 other files (references) in cyberful/builtin/skills/audit-native-memory-safety of cyberful/cyberful.

  • SKILL.md
  • agents/openai.yaml
  • references/memory-unsafe-catalog.md
  • references/native-toolchain-hardening.md

Open the folder on GitHubat commit ec598a6

Compare with similar skills

Audit Native Memory Safety 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.

Audit Native Memory Safety compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Audit Native Memory Safety this skillcyberful/cyberful135—~829Automated safety check: PassAGPL-3.0
Fuzzing Harness Designtrailofbits/skills7.5k1 repos~5.3kAutomated safety check: PassCC-BY-SA-4.0
Fuzzing Obstacle Patchertrailofbits/skills7.5k—~4kAutomated safety check: PassCC-BY-SA-4.0
Code Audit3stoneBrother/code-audit8921 repos~2.7kAutomated safety check: PassNone
Harness Design Fuzzingprovos/ironcurtain612—~5.7kAutomated safety check: PassApache-2.0
ClusterfuzzliteInternationalColorConsortium/iccDEV183—~1.5kAutomated safety check: PassBSD-3-Clause

Similar skills

  • Fuzzing Harness Design

    trailofbits/skills

    Official

    Guides writing and improving fuzzing harnesses for C, C++ and Rust so random byte input gets translated into structured, reproducible test cases for the target code.

    7.5k GitHub starsUsed in 1 repo~5.3k tokens
    SecurityAuto-check passed

  • Fuzzing Obstacle Patcher

    trailofbits/skills

    Official

    Patches checksums, hash checks, time-based seeds and other non-deterministic state out of fuzzing builds so the fuzzer reaches deeper code, with production behavior intact.

    7.5k GitHub stars~4k tokensUpdated today
    SecurityAuto-check passed

  • Code Audit

    3stoneBrother/code-audit

    Professional code security audit skill covering 55+ vulnerability types.

    892 GitHub starsUsed in 1 repo~2.7k tokens
    SecurityAuto-check passed

  • Harness Design Fuzzing

    provos/ironcurtain

    Reference vocabulary for designing instrumented harnesses that drive vulnerability discovery — design classes (trigger-driven vs coverage-driven), tiered scope (T1 isolated function / T2…

    612 GitHub stars~5.7k tokensUpdated 3 days ago
    SecurityAuto-check passed

  • Clusterfuzzlite

    InternationalColorConsortium/iccDEV

    Build, test, or update the iccDEV ClusterFuzzLite libFuzzer integration across ASan, UBSan, and MSan.

    183 GitHub stars~1.5k tokensUpdated today
    SecurityAuto-check passed

  • Constant-Time Analysis

    trailofbits/skills

    Official

    Compiles cryptographic code and inspects the assembly or bytecode for variable-time instructions, then triages which flagged operations actually touch secrets.

    7.5k GitHub stars~3.3k tokensUpdated today
    SecurityAuto-check: notes

More from cyberful/cyberful

All 85 skills in this repo

  • Audit Infrastructure As Code

    cyberful/cyberful

    Audit infrastructure-as-code artifacts for unsafe defaults, policy gaps, privilege exposure, control drift, and deployment-impact evidence.

    135 GitHub stars~649 tokensUpdated 1 mo ago
    Auto-check passed

  • Audit Kubernetes Policy Enforcement

    cyberful/cyberful

    Audit Kubernetes admission and policy-as-code enforcement against local workload manifests, exception paths, namespace scope, and deployment evidence.

    135 GitHub stars~610 tokensUpdated 1 mo ago
    Auto-check passed

  • Audit Pci Dss Penetration Test Evidence

    cyberful/cyberful

    Audit PCI DSS penetration-test methodology, scope, internal and external reports, segmentation results, tester independence, remediation, retesting, retention, and multi-tenant support evidence.

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

  • Operate Content Discovery

    cyberful/cyberful

    Design and interpret advanced content discovery with ffuf and complementary web fuzzers.

    135 GitHub stars~1.5k tokensUpdated 1 mo ago
    Auto-check passed

  • Operate Network Recon

    cyberful/cyberful

    Build a high-fidelity network and service inventory using Nmap, Masscan, packet capture, DNS, and protocol-specific follow-up.

    135 GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed

  • Operate Sast Toolchain

    cyberful/cyberful

    Operate Semgrep and source-oriented static analysis as a hypothesis, coverage, and regression system during advanced code audits.

    135 GitHub stars~1.3k tokensUpdated 1 mo ago
    Auto-check passed

Works with

Categories

Questions about Audit Native Memory Safety

What does Audit Native Memory Safety do?

Audit C, C++, unsafe Rust, native extensions, parsers, codecs, FFI boundaries, and systems code for memory corruption and low-level exploitation risk. Audit Native Memory Safety is an agent skill from cyberful/cyberful. Audit C, C++, unsafe Rust, native extensions, parsers, codecs, FFI boundaries, and systems code for memory corruption and low-level exploitation risk.

When should I use Audit Native Memory Safety?

Audit Native Memory Safety fits situations like: buffer overflows; out-of-bounds access; integer overflow; uninitialized memory.

How do I install Audit Native Memory Safety in Claude Code?

Run `npx skills add cyberful/cyberful --skill audit-native-memory-safety -a claude-code`. Or copy the skill folder (cyberful/builtin/skills/audit-native-memory-safety in cyberful/cyberful) into .claude/skills/audit-native-memory-safety in your project. Claude Code loads it when a task matches its description.

How do I install Audit Native Memory Safety in Codex?

Run `npx skills add cyberful/cyberful --skill audit-native-memory-safety -a codex`. Or copy the skill folder (cyberful/builtin/skills/audit-native-memory-safety in cyberful/cyberful) into .agents/skills/audit-native-memory-safety in your project. Codex loads it when a task matches its description.

Can I use Audit Native Memory Safety 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 cyberful/cyberful --skill audit-native-memory-safety -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/audit-native-memory-safety, .gemini/skills/audit-native-memory-safety, .github/skills/audit-native-memory-safety and .opencode/skills/audit-native-memory-safety in your project.

What does Audit Native Memory Safety need to run?

SKILL.md names no scripts, command-line tools or credentials: Audit Native Memory Safety is instructions for the agent only.

Does Audit Native Memory Safety access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Audit Native Memory Safety 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. Review the folder before installing.

What licence does Audit Native Memory Safety use?

Audit Native Memory Safety is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Audit Native Memory Safety use?

About 829 tokens (SKILL.md is roughly 3.3k 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 1.2k tokens, read only when the agent opens those files.

What are the alternatives to Audit Native Memory Safety?

Skills that share tags, products or a category with Audit Native Memory Safety: Fuzzing Harness Design (trailofbits/skills, 7.5k stars), Fuzzing Obstacle Patcher (trailofbits/skills, 7.5k stars), Code Audit (3stoneBrother/code-audit, 892 stars) and Harness Design Fuzzing (provos/ironcurtain, 612 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Audit Native Memory Safety?

cyberful (a GitHub organization) maintains it in cyberful/cyberful, which has 135 GitHub stars. The repository holds 85 skills in this directory. The repository was last updated on August 24, 2026.

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