runtime-error-explainer

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to read and interpret user-pasted error messages/stack traces ("Use when a user pastes an error they don't understand"), which are arbitrary untrusted user-generated content that the agent uses to decide fixes and next actions, enabling indirect prompt injection.