clawsec-scanner

Warn

Audited by Snyk on Mar 11, 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 fetches public CVE/advisory data from OSV/NVD (scripts/query_cve_databases.mjs and SKILL.md) and includes parsed advisory text and references in generated reports (lib/report.mjs) which the hook handler then posts into conversation messages as system content (hooks/clawsec-scanner-hook/handler.ts), meaning untrusted third‑party advisory content is ingested and can influence agent decisions and outputs.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 11, 2026, 03:22 AM