plan-design-review

Pass

Audited by Gen Agent Trust Hub on Jul 28, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes git and gh (GitHub CLI) commands via the Bash tool. These commands are used to gather technical context, such as identifying the base branch (gh pr view) and listing recent changes (git diff), which are necessary for performing a design review within a software project.
  • [EXTERNAL_DOWNLOADS]: The skill retrieves repository and pull request metadata from GitHub using the official gh CLI. This involves network requests to a well-known service (GitHub) to fetch information required for the review process.
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for Indirect Prompt Injection because it reads and processes data from external project files.
  • Ingestion points: The skill reads TODOS.md, CLAUDE.md, AGENTS.md, DESIGN.md, and various plan documents/branch diffs.
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when reading these files.
  • Capability inventory: The skill possesses the Bash and Edit tools, which allow it to execute shell commands and modify files.
  • Sanitization: There are no explicit instructions to sanitize or validate the content fetched from external files before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 28, 2026, 01:40 PM
Security Audit — agent-trust-hub — plan-design-review