narrative-tracker

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

• Third-party content exposure detected (high risk: 0.90). The skill's Process step 2 explicitly queries external AI platforms (e.g., ChatGPT, Perplexity, Gemini) and "capture[s] the full AI-generated response" to read and interpret those third‑party outputs as part of its workflow, which exposes the agent to untrusted external content that could contain instructions or influence decisions.