skills/2ykwang/agent-skills/docs/Gen Agent Trust Hub

docs

Pass

Audited by Gen Agent Trust Hub on Feb 25, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill enforces a strict document root at docs/generated/ and explicitly prohibits modifications to any files outside this directory, providing a strong security boundary for file operations.
  • [COMMAND_EXECUTION]: The toolset is limited to file system utilities (Glob, Grep, Read, Write, Edit) used for documentation purposes. No arbitrary shell execution or dangerous command patterns were detected.
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by reading source code to generate documentation.
  • Ingestion points: references/write-procedure.md (Step 3) reads source code from paths provided in arguments or found via discovery.
  • Boundary markers: Absent; there are no explicit delimiters or instructions to ignore embedded commands within the analyzed source code.
  • Capability inventory: File system access via Read/Write/Edit/Glob/Grep, limited by policy to the documentation root.
  • Sanitization: Absent; the agent summarizes code intent directly. However, the risk is considered low and inherent to the documentation task.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 25, 2026, 11:38 AM