agentleFS
scoobydont-666scoobydont-666/shared-claude-skills/skills/supply-chain-risk-auditor/SKILL.md

supply-chain-risk-auditor

Skill1 starsChanged 33 days agoMITView on GitHub

Assess dependency provenance, maintenance, release trust and exposure to known compromises using authoritative evidence and exact installed versions.

7 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use the available repository connector, package registry metadata and current vendor advisories.

    line 9
  2. Distinctive:

    Write a report using the report template.

    line 15

“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Supply-chain risk audit

Inventory direct and transitive dependencies from actual lockfiles, installed artifacts and build inputs. Record package ecosystem/name/version, source URL, integrity/provenance, execution phase, permissions and reachable consumer. Include CI actions and install scripts.

Use the available repository connector, package registry metadata and current vendor advisories. A missing gh binary need not block other authorized evidence gathering. Do not install or execute a suspicious package to inspect it.

Assess maintainer/release access controls, provenance, ownership transfers, unusual release changes, supported versions, response to verified vulnerabilities and dangerous capabilities. Popularity, anonymity, number of maintainers or raw CVE counts are signals for investigation, not proof of maliciousness or a standalone high-risk verdict.

Match advisories to exact affected versions and artifact digests. Check whether affected code ran and what credentials/data it could reach. Follow incident verification and indicator handling. A name/string match alone is not confirmation; a missing match is not proof of safety.

Write a report using the report template. Include the complete assessed inventory or a coverage summary so omitted packages are not interpreted as safe. Distinguish confirmed exposure, risk needing investigation, no finding within scope and unavailable evidence.

Recommend proportional fixes, verified supported alternatives and a migration/test plan. Preserve evidence and follow the authorized incident-response process before disruptive containment, credential rotation or reinstall. Do not prescribe a stale 'safe version' from a static skill file.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.