repo-story-time
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute various PowerShell and git commands to explore repository structure and analyze commit history. Specifically, it uses
Get-ChildItemfor file discovery andgit logwith complex filtering/grouping logic to extract metrics (SKILL.md). - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from the repository it is analyzing, creating an attack surface where malicious content in the repository could influence the agent's summary.
- Ingestion points: Reads contents of repository files (markdown, JSON, YAML) and git log output (SKILL.md).
- Boundary markers: None explicitly defined in the instructions to prevent the agent from following instructions embedded within the analyzed data.
- Capability inventory: Uses the
editFilestool to create new files (REPOSITORY_SUMMARY.md,THE_STORY_OF_THIS_REPO.md) to the filesystem (SKILL.md). - Sanitization: No input validation or sanitization mechanisms are specified for the repository data being processed.
Audit Metadata