large-file-refactor
Pass
Audited by Gen Agent Trust Hub on Aug 4, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The Python script
scripts/large-file-refactor.pyexecutes external tools (git,tokei, andrg) usingsubprocess.runwith list-based arguments. This approach is a security best practice that prevents shell injection vulnerabilities. - [DATA_EXPOSURE]: The skill reads the content of local source files to estimate line counts when specialized tools are unavailable. The data is processed strictly for LOC calculation and is not exfiltrated or stored.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted source code as part of its analysis workflow. While this presents a theoretical attack surface, the skill's capabilities are restricted to read-only operations and reporting, and the instructions direct the agent to focus on structural code properties (cohesion, coupling), which limits the impact of potential embedded instructions.
- [SAFE]: The skill uses
uvfor local script execution and includes configuration to restrict implicit invocation, ensuring the agent only runs the analysis when explicitly requested.
Audit Metadata