git-sync
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources which could contain malicious instructions.
- Ingestion points: Data is ingested through
git log,git branch,git remote, andgh pr viewoutput inSKILL.md(Phase 1 and Phase 3). - Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore embedded commands within Git commit messages or PR descriptions.
- Capability inventory: The skill uses subprocess execution via shell commands (
git,gh) as documented inSKILL.md. - Sanitization: There is no evidence of sanitization or filtering of Git metadata before it is processed or displayed by the agent.
- [COMMAND_EXECUTION]: The skill relies on executing shell commands to manage Git repositories.
- Evidence: The skill executes various Git and GitHub CLI (
gh) commands to inspect and modify the repository state, includinggit fetch,git merge,git rebase, andgit push --force-with-lease.
Audit Metadata