documentation-architecture

Pass

Audited by Gen Agent Trust Hub on May 2, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references standard development libraries such as ts-morph and fastapi, and utilizes cdn.jsdelivr.net for loading Swagger UI assets, which is a well-known and trusted service.- [COMMAND_EXECUTION]: Examples provided in the skill documentation include standard shell commands for package management (npm install, pip install) and deployment using wrangler, which are consistent with the skill's purpose as a documentation architecture toolkit.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze project source code to generate documentation, which represents a potential attack surface for indirect prompt injection if the code contains malicious instructions.
  • Ingestion points: Scripts in examples/coverage-validation.md read source files from the ./app directory.
  • Boundary markers: No specific delimiters are identified to separate source code from potentially malicious embedded instructions.
  • Capability inventory: The skill utilizes Read, Write, Grep, and Glob tools to process the codebase.
  • Sanitization: The provided examples do not include explicit sanitization of the content extracted from source files.
Audit Metadata
Risk Level
SAFE
Analyzed
May 2, 2026, 07:43 AM
Security Audit — agent-trust-hub — documentation-architecture