code-stats
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the Bash tool to run local binaries including 'tokei' for statistics, 'difft' for semantic comparisons, and 'jq' for processing output data. It also includes examples for modifying git configurations.
- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill processes local source code files and directory structures to generate reports, which involves reading file contents and directory trees.
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to instructions hidden within the source code it analyzes, as it processes untrusted local data.
- Ingestion points: Local codebase files and git history referenced in SKILL.md and supplemental references.
- Boundary markers: No explicit delimiters are used to separate analyzed code from agent instructions.
- Capability inventory: Shell command execution via Bash tool (tokei, difft, git, jq).
- Sanitization: No content sanitization is performed on analyzed files.
Audit Metadata