apollo-connectors
Warn
Audited by Snyk on Feb 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill's required workflow explicitly instructs fetching and using live API responses and external docs (Step 1: "Fetch relevant documentation from MCP tools or reference files" and Step 4: "Run
rover connector run --schema ..." against the API baseURL like "https://api.example.com"), meaning the agent ingests untrusted, user-specified third-party API responses as part of its processing and decisions.
Audit Metadata