Securing AI Systems
trilwu/secskills
Assess and harden LLM applications and agentic systems against prompt injection, tool misuse, excessive agency, memory poisoning, RAG data leakage, and model supply-chain risk, mapped to the OWASP…
Cross-agent self-inspection of your AI-agent stack. An agent skill from alexgreensh/repo-forensics.
Install Forensify
$ npx skills add alexgreensh/repo-forensics --skill forensify -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install alexgreensh/repo-forensics forensify --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/alexgreensh/repo-forensics.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/forensify .claude/skills/forensify && rm -rf skills-srcUse ~/.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/
Install the "forensify" agent skill from https://github.com/alexgreensh/repo-forensics/tree/main/skills/forensify into .claude/skills/forensify/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "forensify", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/alexgreensh/repo-forensics/tree/main/skills/forensifyType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add alexgreensh/repo-forensics --skill forensify -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install alexgreensh/repo-forensics forensify --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/alexgreensh/repo-forensics.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/forensify .agents/skills/forensify && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "forensify" agent skill from https://github.com/alexgreensh/repo-forensics/tree/main/skills/forensify into .agents/skills/forensify/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "forensify", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add alexgreensh/repo-forensics --skill forensify -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install alexgreensh/repo-forensics forensify --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/alexgreensh/repo-forensics.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/forensify .cursor/skills/forensify && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "forensify" agent skill from https://github.com/alexgreensh/repo-forensics/tree/main/skills/forensify into .cursor/skills/forensify/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "forensify", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/alexgreensh/repo-forensics.git --path skills/forensify--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add alexgreensh/repo-forensics --skill forensify -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install alexgreensh/repo-forensics forensify --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/alexgreensh/repo-forensics.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/forensify .gemini/skills/forensify && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "forensify" agent skill from https://github.com/alexgreensh/repo-forensics/tree/main/skills/forensify into .gemini/skills/forensify/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "forensify", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install alexgreensh/repo-forensics forensifyInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add alexgreensh/repo-forensics --skill forensify -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/alexgreensh/repo-forensics.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/forensify .github/skills/forensify && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "forensify" agent skill from https://github.com/alexgreensh/repo-forensics/tree/main/skills/forensify into .github/skills/forensify/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "forensify", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add alexgreensh/repo-forensics --skill forensify -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install alexgreensh/repo-forensics forensify --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/alexgreensh/repo-forensics.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/forensify .opencode/skills/forensify && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "forensify" agent skill from https://github.com/alexgreensh/repo-forensics/tree/main/skills/forensify into .opencode/skills/forensify/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "forensify", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
forensify- GitHub stars
- 190
- Token cost
- ~2.5k tokens
- SKILL.md length
- 871 words
- Files
- 46 (incl. scripts, references)
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Cross-agent self-inspection of your AI-agent stack. An agent skill from alexgreensh/repo-forensics.
- Works in 6 steps: Skills — prompt injection risk, shadow… → MCP — rug pull enablers (tool… → Hooks & auto-execution — hook scripts… → …
- The user asks to audit their own setup
- SKILL.md covers What makes this different, How it works, The six risk domains and Cross-ecosystem intelligence, plus 7 more sections
- Runs Python scripts from its folder; calls codex
What it does
Forensify is an agent skill from alexgreensh/repo-forensics. Cross-agent self-inspection of your AI-agent stack. Audits skills, MCP servers, hooks, plugins, commands, credentials, and memory files across Claude Code, Codex, OpenClaw, and NanoClaw. Produces a structured inventory and narrative briefing with cross-ecosystem risk analysis. Use when the user asks to audit their own setup, check what they have installed, review their agent stack security posture, or understand cross-tool interactions. Use when a user has accumulated skills/plugins/MCP servers over time and…
Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 49 other files, including scripts and reference files (for example `config/ecosystem_roots.json`, `config/ecosystem_roots.md` and `domains/commands.json`).
It sits in Security, covering MCP servers, Threat modeling and Incident response. It works with Model Context Protocol. The repository describes itself as: Offline security scanner for AI-agent repos, skills, plugins, and MCP servers.
When your agent uses it
- The user asks to audit their own setup
- Check what they have installed
- Review their agent stack security posture
- Understand cross-tool interactions
Example prompts
- “/forensify”
Requirements
- Python 3
- Pre-approved tools (allowed-tools): Bash, Read, Glob, Grep
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Skills — prompt injection risk, shadow skill overrides, cross-ecosystem
- MCP — rug pull enablers (tool descriptions from mutable sources), tool
- Hooks & auto-execution — hook scripts with symlink resolution (Claude
- Plugins & marketplace trust chain — installed plugins, marketplace
- Commands, agents, config & memory — slash commands, subagent definitions,
- Credentials & permissions — structured metadata only. File mode, perms,
What it can do on your machine
Read from SKILL.md and the folder at commit 931e7b9. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
BashReadGlobGrep
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (Python, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
codex
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
Forensify loads about 2.5k tokens when it runs, and up to ~3.4k if it reads all its reference files. Until then it costs about 205 tokens; SKILL.md has 871 words of instructions outside code blocks.
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: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NoteMentions a .env fileSKILL.md:108
read credential values.** `auth.json`, `.env`, OAuth tokens — stat - NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
allowed-tools: Bash, Read, Glob, Grep
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
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 871 words (~2,456 tokens).
“The agent stack you have already installed is your biggest blind spot. repo-forensics catches threats before install. Forensify tells you what is already on this machine, across every agent framework, and where the credential, injection, and auto-execution surfaces are right…”
- name
- forensify
- allowed-tools
- Bash, Read, Glob, Grep
- metadata.author
- Alex Greenshpun
- metadata.version
- 1.0.0
- user-invocable
- true
- argument-hint
- [--target PATH] [--inventory] [--domains NAMES] [--list-runs] [--dry-run] [--format md|json|both] [--include-shadows]
Files
SKILL.md and 45 other files (scripts, references) in skills/forensify of alexgreensh/repo-forensics.
- SKILL.md
- config/ecosystem_roots.json
- config/ecosystem_roots.md
- config/seatbelt_subagent.sb
- domains/commands.json
- domains/credentials.json
- domains/hooks.json
- domains/mcp.json
- domains/plugins.json
- domains/skills.json
- orchestrator/__init__.py
- orchestrator/analysis_dispatcher.py
- orchestrator/contracts.py
- orchestrator/scanner_driver.py
- orchestrator/synthesis_presenter.py
- prompts/domain_commands.txt
- prompts/domain_credentials.txt
- … and 29 more
Open the folder on GitHubat commit 931e7b9
Compare with similar skills
Forensify 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Forensify this skillalexgreensh/repo-forensics | 190 | — | ~2.5k | Automated safety check: Notes | Custom licence | |
| Securing AI Systemstrilwu/secskills | 157 | — | ~2.9k | Automated safety check: Pass | MIT | |
| Plugin Scanneriflytek/skillhub | 5.2k | 2 repos | ~1.1k | Automated safety check: Notes | Apache-2.0 | |
| MCP Gateway SecurityHack23/cia | 239 | — | ~2.4k | Automated safety check: Pass | Apache-2.0 | |
| Skill InspectorNVIDIA/SkillSpector | 20k | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | |
| Golang Pkg Go Devcontext-labs/whip | 1.1k | 2 repos | ~3k | Automated safety check: Pass | MIT |
Similar skills
Plugin Scanner
iflytek/skillhub
Scan AI agent skills, plugins, MCP servers, and agent tooling for prompt injection, unsafe commands, secret exposure, and supply-chain risks before installing or trusting them.
MCP Gateway Security
Hack23/cia
MCP gateway security patterns, token management, request validation, and audit logging for MCP communications
- Official
Skill Inspector
NVIDIA/SkillSpector
Decides whether an agent skill is safe to install by combining a SkillSpector static scan with the agent's own source review, ending in APPROVE, CAUTION or REJECT.
Golang Pkg Go Dev
context-labs/whip
Golang package/module docs via godig, a pkg.go.dev API client (CLI + MCP) — APIs, symbols, versions, importers, licenses, vulnerabilities.
MCP Server Security Audit
awarexone/Agentic-Bug-Hunter
Audits MCP servers and their client configs for tool poisoning, prompt injection, over-privileged tools, injection bugs, secret leaks and missing approval gates.
Related
Works with
Categories
Questions about Forensify
What does Forensify do?
Cross-agent self-inspection of your AI-agent stack. An agent skill from alexgreensh/repo-forensics. Forensify is an agent skill from alexgreensh/repo-forensics. Cross-agent self-inspection of your AI-agent stack.
When should I use Forensify?
Forensify fits situations like: the user asks to audit their own setup; check what they have installed; review their agent stack security posture; understand cross-tool interactions.
How do I install Forensify in Claude Code?
Run `npx skills add alexgreensh/repo-forensics --skill forensify -a claude-code`. Or copy the skill folder (skills/forensify in alexgreensh/repo-forensics) into .claude/skills/forensify in your project. Claude Code loads it when a task matches its description.
How do I install Forensify in Codex?
Run `npx skills add alexgreensh/repo-forensics --skill forensify -a codex`. Or copy the skill folder (skills/forensify in alexgreensh/repo-forensics) into .agents/skills/forensify in your project. Codex loads it when a task matches its description.
Can I use Forensify 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 alexgreensh/repo-forensics --skill forensify -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/forensify, .gemini/skills/forensify, .github/skills/forensify and .opencode/skills/forensify in your project.
What does Forensify need to run?
Going by SKILL.md and its folder, Forensify needs Python for the scripts in its folder and the command-line tools its instructions call (codex). Our summary lists: Python 3. Its frontmatter pre-approves these tools: Bash, Read, Glob, Grep.
Does Forensify 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 Forensify safe to install?
Our automated static check of SKILL.md found notes only (mentions a .env file; pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. 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 Forensify use?
Forensify has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does Forensify use?
About 2.5k tokens (SKILL.md is roughly 9.8k 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 941 tokens, read only when the agent opens those files.
What are the alternatives to Forensify?
Skills that share tags, products or a category with Forensify: Securing AI Systems (trilwu/secskills, 157 stars), Plugin Scanner (iflytek/skillhub, 5.2k stars), MCP Gateway Security (Hack23/cia, 239 stars) and Skill Inspector (NVIDIA/SkillSpector, 20k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Forensify?
alexgreensh (a GitHub user) maintains it in alexgreensh/repo-forensics, which has 190 GitHub stars. The repository was last updated on September 27, 2026.
Source: alexgreensh/repo-forensics on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.