review-perf-ruby
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data (Ruby source code and git diffs), which presents a risk of indirect prompt injection.
- Ingestion points: Processes branch diffs, local Ruby files, and pull request content provided by the user in
SKILL.md. - Boundary markers: The instructions do not define strict delimiters (e.g., XML tags or specific markers) to isolate the code-under-review from the agent's core instructions.
- Capability inventory: The skill instructs the agent to read local file context and use external documentation lookup tools like Dash MCP and Context7. It also suggests using existing local benchmarks or profiling output if they are present.
- Sanitization: There are no instructions provided to sanitize the input or to explicitly ignore natural language instructions that might be embedded within the analyzed code comments.
Audit Metadata