ns-best-practices

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill identifies security and accessibility issues by scanning user-provided source code and configurations. This ingestion of untrusted data creates a potential for indirect prompt injection if those files contain malicious instructions.
  • Ingestion points: Local source code files, API gateway configurations (e.g., nginx, Laravel middleware), and static assets specified during the workflow.
  • Boundary markers: No explicit markers or 'ignore' instructions are defined for the file-scanning phase to mitigate potential injections in audited content.
  • Capability inventory: The agent can read local files, report security vulnerabilities, and implement 'minimal safe diffs' upon user request.
  • Sanitization: The instructions do not describe sanitization or validation steps for the content of files before they are processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 10:21 PM
Security Audit — agent-trust-hub — ns-best-practices