deep-brainstorm
Warn
Audited by Snyk on Mar 24, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill's EXPLORE phase explicitly allows spawning web-search-researcher subagents ("Using Subagents for Research (Sparingly)" with Task(subagent_type="web-search-researcher", ...)), which fetch open-web third‑party content that the agent will read and use to inform exploration and decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata