waves-codex
Warn
Audited by Snyk on Aug 20, 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). The skill’s runtime workflow can read outsider-authored free text via “External research” browsing in worker slices (e.g., vendor status pages and community forums) as described in the evaluation handoff and the “pull from attached resources… (docs, MCP, web)” step.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata