git-time-travel
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill documents and encourages the use of shell commands for git operations, including git bisect run. This command allows the execution of arbitrary test scripts or binaries such as npm test or ./test-for-bug.sh over a range of commits.
- [INDIRECT_PROMPT_INJECTION]: The skill core functionality involves reading and interpreting git history, which constitutes an untrusted data source that could contain malicious instructions designed to subvert the agent.
- Ingestion points: Git history data is ingested via commands like git log, git blame, and git show as specified in references/patterns.md.
- Boundary markers: There are no boundary markers or instructions to treat commit messages as untrusted text, leaving the agent susceptible to instructions embedded in commit logs or code comments.
- Capability inventory: The skill enables shell command execution through git and provides patterns for running arbitrary scripts via git bisect run.
- Sanitization: No sanitization or content validation is performed on the data retrieved from the git repository before it is processed by the agent.
Audit Metadata