cleanup-project

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

• Third-party content exposure detected (high risk: 0.90). SKILL.md's "Restoration" section explicitly instructs fetching skill files from a public GitHub raw URL (https://raw.githubusercontent.com/ar4mirez/samuel/...), meaning the agent would ingest public, potentially untrusted third‑party content that could contain instructions affecting subsequent actions.