Trusting the code you did not write: lockfiles and the integrity they give, dependency risk and update discipline, vendoring versus fetching, artifact signing and provenance verification, lockfile maintenance across a fleet, and the written supply-chain record. It explains how to make third-party code a managed input; it never recommends a registry and never promises safety. Use when asking "lockfile", "supply chain attack", "dependency confusion", "provenance", "artifact signing", "should I vendor", "pinned dependency", "typosquatting", "lockfile drift", "dependency update discipline", "security release across a fleet", "lockfile merge review", "exception log with expiry", "dormant repository updates", "where did this package come from". Not for vulnerability management of shipped code (ac-security-engineer), not for upgrade planning within one codebase (ac-codebase-maintenance), not for secure coding practices (ac-code-construction).
cp -r cryptoskill/skills/exchanges/anoscranel-ac-software-supply-chain .claude/skills/clawhub install anoscranel-ac-software-supply-chainCapabilities below are detected automatically by an open-source scanner that reads the skill's text and scripts (see how this is computed). Not measured means the scanner couldn't make a confident call — it is NOT a green check, and you should treat it as a possible red flag until a human or a stronger scanner has measured it.
read_only Phase 1 single-mode classification — multi-mode breakdown deferred to Phase 2.
We did not find any well-known hosted services in this skill's text or scripts. This does NOT mean the skill is local-only — it might use services we don't yet recognize, or talk to them through code paths our scanner can't reach. A complete dependency list (every package, library, and binary, with integrity hashes) is on the roadmap; today we only show recognized hosts.
No one has audited this skill yet. That is different from “audited and clean” — it just means no professional reviewer (a security firm, the CryptoSkill team, or a verified independent researcher) has signed off on it. There are no audit reports to read. How reviewer levels work →
SKILL.md → SOURCE.md → TRUST.auto.yaml → Browse directory →
Auto-generated by cryptoskill/extract-capabilities/0.3.1 · hosted-service list version 2026-09-06 · how this is computed