create-prd

Pass

Audited by Gen Agent Trust Hub on Jun 3, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill operates as a structured text generation tool. It processes user-supplied business context to produce markdown documentation across 14 predefined chapters, following a logic-based sequence defined in SKILL.md.
  • [COMMAND_EXECUTION]: The repository includes administrative Python scripts (scripts/install_skill.py and scripts/build.py). These scripts perform standard local file operations, such as copying files to the ~/.claude/skills/ directory for installation and concatenating markdown files into a single distribution prompt. These are legitimate development and deployment tools with no malicious behavior identified.
  • [DATA_EXPOSURE]: No hardcoded credentials, API keys, or sensitive environment variable access was found. The skill instructions focus entirely on the transformation of business requirements into structured PRD content.
  • [REMOTE_CODE_EXECUTION]: There are no patterns suggesting the download or execution of remote scripts. Dependencies used in the Python scripts are restricted to the standard library (os, re, shutil, pathlib).
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 3, 2026, 06:21 AM
Security Audit — agent-trust-hub — create-prd