complexity-hotspots
Pass
Audited by Gen Agent Trust Hub on Jun 21, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill attempts to execute standard static analysis tools such as
radon,lizard, andgocycloif they are installed on the local system to calculate code metrics. - [PROMPT_INJECTION]: There is an indirect prompt injection surface as the skill processes content from local repository files. Maliciously crafted content within code files could attempt to influence the agent's final report or refactoring suggestions.
- Ingestion points: Local source code files (Python, JavaScript, Go, etc.)
- Boundary markers: None specified in the workflow.
- Capability inventory: Execution of local command-line analysis tools via shell.
- Sanitization: No specific sanitization or escaping of file content is described before generating suggestions.
Audit Metadata