serpapi
Warn
Audited by Snyk on May 3, 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 instructs the agent to query SerpApi (public search engine results) via the Membrane actions workflow in SKILL.md (e.g., "Search using a natural language description..." and "The result is in the
outputfield of the response"), which clearly fetches untrusted third‑party web content that the agent is expected to read and act on, allowing that content to influence subsequent tool use.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata