gs-openspec-review-change

Pass

Audited by Gen Agent Trust Hub on Nov 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided documentation files (proposal.md, design.md, etc.) as its primary input. These files represent untrusted data that could contain instructions designed to influence the behavior of the agent or its subagents.
  • Ingestion points: The skill reads files from the openspec/changes/<change-id>/ directory during the 'Pre-read' phase (SKILL.md, Step 2).
  • Boundary markers: There are no explicit boundary markers or instructions to ignore embedded prompts within the processed files before passing them to the specialists.
  • Capability inventory: The agent has the ability to read and write files within the project directory and invoke subagents (specialists).
  • Sanitization: No sanitization or escaping of the input data is performed before processing.
  • [COMMAND_EXECUTION]: The skill performs shell commands to gather context and manage the installation process.
  • Context Gathering: The workflow (SKILL.md, Step 2) involves executing git log --oneline -20 and git status on specific directories to verify the environment state.
  • Installation: The README instructs users to run npx skills add agoodway/goodstack, which is the standard installation mechanism for this vendor's tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 19, 2026, 04:36 PM