security-best-practices

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill acts on untrusted user data within its security audit and validation examples, creating a surface for indirect prompt injection attacks.
  • Ingestion points: Untrusted data enters the context via the req.body and userInput variables in the Node.js and validation code snippets.
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are included in the skill's guidance to isolate data from the agent's instructions.
  • Capability inventory: The skill does not possess autonomous capabilities such as network access or file system modification; it primarily serves as an educational template.
  • Sanitization: The skill provides best-practice examples for sanitizing input using Joi and DOMPurify, and explicitly demonstrates the use of parameterized queries to prevent SQL injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 01:50 PM