reviewing-rails-code
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes
git ls-files,git diff, andrg(ripgrep) to perform codebase discovery and pattern searching. These commands are scoped to repository metadata and text searching within the project directory to support the code review process. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data by reading Ruby source files (
.rb) from the user's repository. - Ingestion points: Source code files identified during the 'Resolve the scope' step in
SKILL.md. - Boundary markers: None explicitly defined to isolate analyzed code from agent instructions.
- Capability inventory: Includes shell command execution (
git,rg) and file system access. - Sanitization: The skill instructions do not specify sanitization or escaping of the ingested code content before processing.
- [SAFE]: The skill provides instructions for the user to install a complementary skill from the author's own repository (
bostonaholic/skills). As this is a vendor-owned resource, it represents standard modular functionality and does not introduce external risk.
Audit Metadata