wibaek-review-diff-scan
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data such as Git diffs and source code files.
- Ingestion points: Git diff targets and supporting repository files specified in SKILL.md.
- Boundary markers: The instructions do not define explicit delimiters to separate analyzed code from agent instructions.
- Capability inventory: The agent can execute shell commands including git, lint, and test suites as described in SKILL.md.
- Sanitization: There is no evidence of content sanitization or instruction-ignoring logic for the data being reviewed.
- [COMMAND_EXECUTION]: The skill utilizes local shell commands to perform its primary function of code review.
- Evidence: SKILL.md lists git diff, lint, format check, typecheck, and unit/integration tests as recommended commands. These are standard engineering tools used within the scope of the skill's purpose.
Audit Metadata