expand-tasks
Warn
Audited by Snyk on Aug 5, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). In SKILL.md, the “research-expander” agents generate targeted research queries (including WebSearch as a last resort) and run them via the user-configured research provider/MCP tools, which means outsider-authored content can be ingested when the provider fetches pages or search results.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata