github

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

• Third-party content exposure detected (high risk: 0.75). The required workflow uses GitHub API calls to fetch PR/issue details (e.g., via getPR() / getIssue() / search routes), and those responses can include outsider-authored free text like issue/PR bodies, comments, and review text that would be ingested into the agent’s LLM context.