smart-commit
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local git commands and a vendor script (scripts/run-skill.sh) using the Bash tool to perform commit operations and diagnostics.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted data from the repository.
- Ingestion points: Data enters the agent context via git diff, git log, and git status output (SKILL.md).
- Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the processed repository data.
- Capability inventory: The skill has access to Bash, Read, Grep, and Glob tools.
- Sanitization: It includes logic to strip specific AI-related trailers from commit messages but lacks general sanitization for content derived from the codebase.
Audit Metadata