gentle-ai-issue-creation

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow explicitly instructs the agent to "Search existing issues → confirm it's not a duplicate" (https://github.com/Gentleman-Programming/gentle-ai/issues) — i.e., ingest and interpret public, user-generated GitHub issues — which can materially influence whether the agent opens or refrains from opening an issue, so untrusted third-party content could induce indirect prompt injection.