skill-auditor

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill explicitly clones public GitHub repositories (Phase 0: "git clone --depth 1 --single-branch ") and then reads SKILL.md and all files in the cloned repo (Phase 1), so it ingests untrusted, user-generated third‑party content which is analyzed and used to drive audit verdicts and installation decisions, allowing indirect prompt-injection vectors.