product-specify

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes content from repository files (e.g., README.md, AGENTS.md) which may contain untrusted input. This input is used to generate Product Decision Records (PDRs).
  • Ingestion points: SKILL.md (Phase 2) reads local project files into the agent context.
  • Boundary markers: No specific delimiters or "ignore" instructions are defined for the ingested content.
  • Capability inventory: The skill has permissions to create directories and write .md files in the .adlc/drafts/pdr/ path.
  • Sanitization: No explicit sanitization or validation of the ingested markdown content is performed before interpolation.
  • [COMMAND_EXECUTION]: The skill invokes local shell and PowerShell scripts (scripts/bash/setup-product-specify.sh, scripts/powershell/setup-product-specify.ps1) to initialize the environment. These scripts perform routine operations such as directory creation, file counting, and project root resolution via git.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 11:02 PM
Security Audit — agent-trust-hub — product-specify