to-issues

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime workflow explicitly fetches an issue’s full body and comments from the issue tracker when the user supplies an issue reference (issue number/URL/path), so outsider-authored free text from other contributors can be ingested into the agent’s LLM context via the issue-tracker fetch/read step.