codify

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

• Third-party content exposure detected (medium risk: 0.65). SKILL.md Step 1 requires reading project docs and commit history (outsider-authored if the project content was not authored by the operating user), and that readable text is then used to classify/routings and generate diffs—so the LLM context can include outsider free text via the project layer scan.