cursor-git-integration

Pass

Audited by Gen Agent Trust Hub on Apr 4, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions and examples for executing standard Git commands (e.g., git merge, git checkout, git stash) within the terminal to facilitate version control workflows.
  • [PROMPT_INJECTION]: The skill facilitates the ingestion of external Git repository data into the agent's context for analysis and review purposes.
  • Ingestion points: Repository content such as diffs and commit history enters the context via the @Git context selector and terminal command outputs (e.g., git show) as documented in SKILL.md and references/ai-powered-git-workflows.md.
  • Boundary markers: The provided instructions do not specify or implement delimiters to separate untrusted repository data from the agent's core instructions.
  • Capability inventory: The skill environment utilizes tools with significant permissions, including arbitrary shell execution (Bash) and full file system access (Read, Write, Edit).
  • Sanitization: There are no documented sanitization or validation procedures for the data retrieved from Git before it is processed by the AI.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 4, 2026, 03:56 PM