studio-develop-design-review
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute
git status --porcelain,git diff, and the shelldatecommand. These operations are used to identify modified UI components and timestamp generated reports, which aligns with the skill's primary purpose as a developer tool. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the repository, specifically content from the
git diffanddocs/DESIGN.md. This content is interpolated into a structured report and a "paste-ready fix prompt" designed for other coding agents. The lack of strict boundary markers or sanitization could allow malicious strings embedded in the codebase to influence the reviewing agent or pass harmful instructions to the downstream agent receiving the fix prompt. - Ingestion points:
git diff(working tree and index),docs/DESIGN.md, and optional project files likedocs/PRODUCT.md. - Boundary markers: Absent. The instructions do not specify delimiters or "ignore embedded instructions" warnings for the external data being analyzed.
- Capability inventory: The skill reads local files, executes git commands, creates directories (
mkdir -p), and writes new report files to the filesystem. - Sanitization: Absent. Offending values from the diff are copied directly into findings and generated prompts without escaping or validation.
Audit Metadata