release-audit

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 is a repo-shape detector and router that reads the target repository’s files (e.g., README/docs/CI configs) at runtime, so any outsider-authored text in those files can be ingested into the LLM context via the “detect what the repo actually ships” step.