pre-pr-greptile

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

• Third-party content exposure detected (medium risk: 0.65). SKILL.md’s required workflow runs greptile review -b <base> --agent (plain-text fallback) and then the agent uses that review output for triage; since that review text is produced by an external service (outsider-authored content) and is ingested into the agent’s LLM context, it creates an indirect prompt-injection risk.