gob-curl

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly instructs the agent to fetch and parse untrusted, user-generated content from public Gerrit endpoints (e.g., https://dart-review.googlesource.com/changes//detail and /comments) as well as Buildbucket/logs.chromium.org build logs, and to use those messages/CI results to decide CL status and next actions, so third‑party content could materially influence behavior.