skills/emmraan/agent-skills/express/Gen Agent Trust Hub

express

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill describes building web applications that ingest untrusted data through HTTP requests, which is an inherent property of web servers.
  • Ingestion points: The skill documents methods for accessing untrusted data via req.body, req.query, req.params, req.headers, and req.ip in SKILL.md.
  • Boundary markers: While not applicable to the documentation itself, the skill instructs on setting up specific route handlers to isolate request processing.
  • Capability inventory: The documented functionality includes network listening (app.listen), static file serving (express.static), and general HTTP response capabilities.
  • Sanitization: The skill proactively recommends security-focused middleware including helmet for security headers, cors for cross-origin resource sharing, and express-rate-limit for DDoS protection in the 'Production hardening' section.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 11:35 AM
Security Audit — agent-trust-hub — express