research
Warn
Audited by Snyk on Jul 5, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). At runtime the skill may use “WebFetch → WebSearch” to fetch arbitrary public web pages (outsider-authored content) and then read their text into the agent context to extract API/config details.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata