qa-review

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

• Third-party content exposure detected (high risk: 0.70). The skill’s workflow is a QA review that instructs the agent to read the ticket/issue/PR description and inspect the diff; those artifacts are typically outsider-authored free text (e.g., issue/PR descriptions or comments by non-operating users) that the agent may ingest into the LLM context.