skills/rockcookies/skills/git-master/Gen Agent Trust Hub

git-master

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect prompt injection vulnerability surface. The skill is designed to read and analyze the last 30 commit messages via git log to adapt its communication style and formatting. This process ingests untrusted data from the repository history which could contain malicious instructions designed to influence the agent.
  • Ingestion points: Commit messages retrieved via git log -30.
  • Boundary markers: No explicit markers or instructions are provided to the agent to ignore potentially malicious content within the commit history.
  • Capability inventory: Access to local Git repository history and the ability to execute Git commands.
  • Sanitization: The skill lacks any mechanism to sanitize or filter the content of commit messages before processing them for style detection.
  • [COMMAND_EXECUTION]: The skill provides various shell-based Git commands for history management, including git log, git blame, and git bisect. While these are legitimate tools for the skill's purpose, they grant the agent the capability to execute commands that traverse and interact with the local filesystem's metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 01:37 PM