git-commit
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local system commands including
gitfor repository management andpython3to run a bundled versioning script (scripts/calver.py). These operations are core to the skill's functionality. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from the local Git repository, such as output from
git status,git diff, andgit tag -l. This untrusted external data is used to generate commit messages and determine version numbers. - Ingestion points: The skill reads
git status,git diff, andgit tag -l(referenced inSKILL.mdandscripts/calver.py). - Boundary markers: The skill defines a strict
Commit Messagetemplate, but does not specify delimiters for wrapping raw diff content during the processing phase. - Capability inventory: The skill possesses the ability to modify the local file system via
git commit, access the network viagit push, and manipulate repository history viagit rebase. - Sanitization: The
scripts/calver.pyscript uses regular expressions to validate existing tags, but the instructions do not explicitly mandate sanitization for user-provided or repository-sourced strings before inclusion in commit messages.
Audit Metadata