afk-to-issues

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime workflow can fetch an outsider-authored issue (via a user-provided issue URL/number/path) and then reads the full body and comments from the external issue tracker, which is free text authored by others and is ingested into the agent’s LLM context.