rp-discovery

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

• Third-party content exposure detected (medium risk: 0.65). The required workflow runs a platform-specific source adapter capture (e.g., rp-source-wordpress/scripts/), which at runtime reads from the source system’s API/exports and produces raw discovery dumps that the skill then synthesizes into source-profile.md / source-schema.json; if that source content includes outsider-authored free text (e.g., posts/comments/media metadata), it can be ingested into the agent’s LLM context via the adapter’s captured outputs.