mece-plan-review

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly runs gh repo list ${GITHUB_ORG} (Step 0-4) to discover related GitHub repos and then instructs the Wiki Researcher and BB Analyst to call read_wiki_structure / read_wiki_contents and WebFetch to ingest repo wikis and external docs (user-generated/public GitHub content and public web pages), and those fetched third‑party artifacts are consumed by subagents and the Red Team to make analysis and remediation decisions that drive file updates—so untrusted third‑party content can materially influence the agent's actions.