battlecard-doc
Warn
Audited by Snyk on Feb 27, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill's workflow explicitly uses external resources (e.g., search_resources({ query }) which includes "uploaded docs, URLs, Google Drive files") and even offers to "create a basic comparison from web research" (Error Handling), and it requires populating the battlecard with that gathered content — meaning untrusted public/web content would be ingested and can materially influence the generated recommendations and subsequent actions.
Audit Metadata