brainstorm-search-plan
Warn
Audited by Snyk on May 15, 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). This skill's Phase 2 "Search" workflow explicitly requires calling the
/searchskill which "iterates across web + MCP tools" to gather citation-backed facts from public websites, and those external search results are fed back into the Brainstorm/Plan loop to drive vendor/library/approach decisions (SKILL.md Phase 2), exposing the agent to untrusted third-party content that can influence actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata