relay

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to read task evidence from external, user-generated sources—e.g., "gh issue view " in SKILL.md Step 1 and the prompt-template's derived from GitHub issues/user descriptions—which are consumed to build dispatch prompts and drive executor actions, so untrusted third-party content can influence behavior.