github

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

• Third-party content exposure detected (high risk: 0.85). The required workflow uses gh issue view ... --json title,body,comments and gh pr view ... --json ... body ... / gh api .../comments --jq ... body, which ingests outsider-authored GitHub issue/PR text (e.g., issue/PR bodies and comment bodies written by other users) into the agent’s LLM context via the CLI/API response.