gr-geo-cite

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

• Third-party content exposure detected (high risk: 0.70). The skill's weekly-cite-check workflow explicitly queries external AI services (Anthropic/OpenAI/Perplexity/Gemini) and ingests their free-text responses (scripts/weekly-cite-check.py and the SKILL.md "Step 2/Step 3" workflow), then parses those untrusted third‑party outputs to extract domains and context that affect reporting and follow-up actions, creating a clear avenue for indirect prompt injection.