security-ownership-map

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

• Third-party content exposure detected (high risk: 0.75). The skill runs git log --name-only over the target repository and ingests the resulting commit metadata and touched file paths (including any outsider-authored commits in that repo) into generated JSON/CSV artifacts that are then read by scripts/query_ownership.py and placed into the agent’s LLM context as bounded JSON output.