skills/vudovn/ag-kit/api-patterns/Gen Agent Trust Hub

api-patterns

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted data from project files, creating a surface for indirect prompt injection.
  • Ingestion points: The scripts/api_validator.py script reads and analyzes source code files and OpenAPI specifications (e.g., .ts, .py, .json, .yaml) from the user's project directory.
  • Boundary markers: There are no explicit instructions or delimiters that help the agent distinguish between its own system instructions and the content of the files it is analyzing.
  • Capability inventory: The skill allows the use of Read, Write, Edit, Glob, and Grep tools, which provides a significant capability set that could be misused if an injection successfully occurs.
  • Sanitization: The validation script extracts data such as API paths and method names directly from files and includes them in its output without sanitization, providing a vector for malicious instructions to reach the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 01:59 PM
Security Audit — agent-trust-hub — api-patterns