review-ruby-code
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands to interact with the repository and run analysis tools, including
git,rubycritic, andbundle exec rspec. These are standard operations for a code review and testing workflow. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data from the codebase which creates a surface for indirect prompt injection via malicious code or comments.
- Ingestion points: Analyzes Ruby source files (.rb) identified via
git diffand parses JSON output fromrubycriticandsimplecov. - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded prompts within the files it reviews.
- Capability inventory: The agent can execute shell commands, read files, and write a summary report (REVIEW.md).
- Sanitization: There is no evidence of sanitization or escaping of the code content before it is processed for design rule violations.
Audit Metadata