writing-git-commits
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses Git commands including
git status,git diff, andgit committo perform its primary function of version control management. These are legitimate uses of the tool's capabilities.- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it is instructed to read and process local git diffs which may contain untrusted data. - Ingestion points: The agent reads the output of
git diff --cachedandgit status --short(SKILL.md). - Boundary markers: There are no explicit markers or safety instructions provided to the agent to treat the diff content as potentially untrusted data.
- Capability inventory: The skill allows the agent to modify the repository state via
git addandgit commit(SKILL.md). - Sanitization: The skill does not implement any validation or sanitization of the content extracted from the git diffs before using it to draft messages or create commits.
Audit Metadata