skill-stocktake
Warn
Audited by Snyk on Apr 7, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The SKILL.md Phase 2 Quality Evaluation explicitly instructs the launched subagent to "use WebSearch if tool names / CLI flags / APIs are present" (Phase 2 checklist), meaning the agent will fetch and read public web pages and other third-party content which can materially influence verdicts and subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata