code-review
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses user-supplied references (e.g., branch names, commit SHAs) directly in shell commands such as
git diff <fixed-point>...HEADandgit rev-parse <fixed-point>. If the execution environment does not properly sanitize these arguments, it could be vulnerable to command injection. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from repository content, including commit messages, code diffs, and external spec files. This content is interpolated into sub-agent prompts for the 'Standards', 'Spec', and 'Frontend' lanes without boundary markers or sanitization.
- Ingestion points: Git diff output, commit logs, untracked files, and spec files (e.g.,
docs/,specs/). - Boundary markers: Absent in sub-agent prompts.
- Capability inventory: Shell execution (git commands), file system read access, and tool invocation (
/frontend-review,/setup-universal-agent-skills). - Sanitization: No evidence of sanitization or escaping of external content before interpolation.
Audit Metadata