ai-supply-chain-security
Skill1 starsChanged 3 months agoApache-2.0View on GitHub
Use when auditing AI-agent supply chain risk, prompt or skill provenance, dependency trust, SBOM/SLSA evidence, MCP tool-poisoning, package provenance, or agent runtime guardrails before release.
In this repository19 other files it gives its agents.
- AGENTS.mdAGENTS.md
- agent-loop-designSkill
- anti-slop-pr-and-writingSkill
- authoring-portable-skillsSkill
- brainstormingSkill
- cross-language-portSkill
- giving-code-reviewSkill
- handoffSkill
- incident-responseSkill
- pr-review-and-releaseSkill
- receiving-code-reviewSkill
- refactoring-safelySkill
- systematic-debuggingSkill
- test-driven-developmentSkill
- using-agtmlsSkill
- verification-before-completionSkill
- vetting-a-skill-before-installSkill
- web-research-and-source-triageSkill
- writing-plansSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 21
Use this skill to audit agentic supply-chain risk before shipping an AI-enabled repository or skill pack.
- Distinctive: line 26
Check provenance: source commit, generator script, checksum, license, and owner.
- Distinctive: line 27
Check package risk: dependency confusion, typosquatting, unsigned artifacts, unpinned install commands, and shell-pipe installers.
- Distinctive: line 28
Check agent risk: prompt injection, MCP tool poisoning, unreviewed network access, file-write authority, and secret handling.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
AI Supply Chain Security
Use this skill to audit agentic supply-chain risk before shipping an AI-enabled repository or skill pack.
Workflow
- Identify generated artifacts, skills, prompts, tools, MCP servers, and provider adapters.
- Check provenance: source commit, generator script, checksum, license, and owner.
- Check package risk: dependency confusion, typosquatting, unsigned artifacts, unpinned install commands, and shell-pipe installers.
- Check agent risk: prompt injection, MCP tool poisoning, unreviewed network access, file-write authority, and secret handling.
- Require release evidence:
SBOM.spdx.json,provenance.json,SHA256SUMS, and greenagtmls.py check. - Report blocking issues before publishing or installing globally.
Evidence
Record reviewed files, commands run, and residual risks in the evidence log when available.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.