req-analyze
Warn
Audited by Snyk on Apr 20, 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's Phase 2 "Web Research Cascade" (see Phase 2: Web Research Cascade in SKILL.md and references/research-cascade.md) explicitly invokes agent-browser, WebSearch, and WebFetch to read full web pages and incorporate "domain findings" into the analysis, meaning it fetches and ingests untrusted public web content that can influence the agent's decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata