airparser
Warn
Audited by Snyk on Mar 4, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md explicitly instructs the agent to retrieve and parse user-provided documents from Airparser (e.g., "Get Document", "List Documents") and to proxy API requests, so untrusted third-party document content could be read and materially influence subsequent actions.
Audit Metadata