gs-reflect
Warn
Audited by Snyk on Nov 19, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). Reviewers are instructed (SKILL.md:33 and each reviewer prompt) to use MCP connectors to read tickets, chat threads, and traces the transcript cites, and those sources can contain outsider-authored text (for example, externally filed tickets or chat messages) that the LLM ingests without the agent independently selecting them.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata