pre-commit-audit
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes scoped Bash utilities such as
git,grep,stat, andfindto inspect the local repository state, file metadata, and contents during the audit process. - [DYNAMIC_EXECUTION]: The skill executes a bundled Python script (
scripts/check_invisible_unicode.py) viauv runto perform deterministic analysis of Unicode characters. This execution is confined to the local environment and the skill's own code. - [INDIRECT_PROMPT_INJECTION]: The skill processes content from the user's filesystem to generate security and anonymity audit reports.
- Ingestion points: Files identified by
git diffinSKILL.mdand read by the bundled Unicode analysis script. - Boundary markers: Not explicitly implemented for the auditing output table.
- Capability inventory: The skill is granted access to common file-inspection utilities (
git,grep,stat,find,uv) and the ability to prompt the user viaAskUserQuestion. - Sanitization: Shell command snippets include variable quoting to prevent command injection through malformed filenames.
Audit Metadata