prd-generator

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill's workflow in SKILL.md involves executing mkdir -p .prd to ensure the storage directory exists. This is a standard file system operation necessary for the skill's file-saving functionality.\n- [PROMPT_INJECTION]: The skill facilitates the processing of untrusted user data (Product Brief) into generated files, creating an indirect prompt injection surface. Evidence Chain: 1. Ingestion points: User-provided input via the workflow in SKILL.md. 2. Boundary markers: None; the skill does not use specific delimiters to isolate user content. 3. Capability inventory: Writing files and creating directories as specified in SKILL.md. 4. Sanitization: None; input is directly used to populate document sections. This surface is considered safe as it is a core component of the documentation generation process.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 07:19 PM
Security Audit — agent-trust-hub — prd-generator