custom-agent-definitions
Warn
Audited by Snyk on Apr 21, 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.md examples for the "research-agent" and "Read-Only Research Agent" explicitly grant and instruct use of WebSearch/WebFetch (allowed-tools: WebSearch, WebFetch, Read) so the agent will fetch and interpret untrusted public web content as part of its workflow, enabling indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata