database-lookup
Warn
Audited by Snyk on Jul 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). SKILL.md instructs the agent to “Make the API call(s)” to public REST endpoints and then “Return results” including the raw JSON; those responses are outsider-authored data fetched at runtime and become LLM-readable context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata