code-necromancer

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests arbitrary GitHub organization repositories (scripts/scan-repos.sh uses gh repo list ORG ... and analyze-repo.sh/other references parse READMEs, code, and docs), so the agent will read untrusted, third‑party/user-generated content from the open web.