policy-as-code-generator

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-supplied natural language compliance requirements to generate executable code. While this represents a potential surface for indirect prompt injection, it is the primary purpose of the skill.
  • Ingestion points: Natural language compliance requirements provided as command-line arguments to the generate-policy.js script in SKILL.md.
  • Boundary markers: The prompt templates utilize double-quote delimiters to encapsulate user input within the shell command.
  • Capability inventory: The skill utilizes Bash, Write, and Edit tools to execute code generation and save the resulting policy files.
  • Sanitization: Input is processed by a local script (plugins/grc-engineer/scripts/generate-policy.js) belonging to the skill author.
  • [COMMAND_EXECUTION]: The skill executes a local Node.js script located at plugins/grc-engineer/scripts/generate-policy.js. This script is a vendor-owned resource used to implement the core functionality of the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 12:26 PM
Security Audit — agent-trust-hub — policy-as-code-generator