windsurf-git-integration
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is composed entirely of Markdown documentation and reference guides. It contains no executable scripts (Python, JavaScript, Bash) or binary files, significantly reducing the risk of direct malicious behavior.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the AI agent to process external data such as Git commit history, staged changes, and branch names to provide suggestions. This creates a surface for indirect prompt injection if the repository contains malicious metadata.
- Ingestion points: Git repository history, staged changes, and branch naming patterns are processed by the agent (referenced in implementation.md and examples.md).
- Boundary markers: The skill does not specify the use of delimiters or ignore-instructions to isolate Git data from agent prompts.
- Capability inventory: The skill uses high-privilege tools including Bash, Read, Write, and Edit for Git operations.
- Sanitization: No specific sanitization or validation logic is provided for external Git content.
Audit Metadata