Project Intake

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

• Third-party content exposure detected (high risk: 0.70). This skill’s required workflow instructs the agent to read repository files like README.md and other project metadata (e.g., SKILL.md:27-46, SKILL.md:85-91), which are outsider-authored when the repository content is not authored by the operating user, and that readable text would be ingested into the LLM context during intake.