git-history-detective
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of data from local Git repositories, which serves as a potential surface for indirect instructions from untrusted sources (like commit messages or file content) to influence the agent's logic. * Ingestion points: Commit history and file contents read via Git CLI commands defined in SKILL.md. * Boundary markers: Absent; there are no specific markers or instructions to delimit or ignore instructions embedded in the repository data. * Capability inventory: The skill utilizes shell execution for Git commands and local testing tools like npm as specified in SKILL.md. * Sanitization: Absent; the skill does not include steps to sanitize or filter data retrieved from the repository history.
Audit Metadata