resolving-merge-conflicts
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of natural language guidance and configuration metadata for Light integration. It does not include any executable scripts, shell commands, or network operations.
- [INDIRECT_PROMPT_INJECTION]: The instructions involve the agent reading external data such as git commit messages, PR descriptions, and conflict markers. This represents a standard attack surface for development tools where untrusted content in a codebase could attempt to influence the agent. The skill mitigates this by instructing the agent to run automated checks (tests, typechecks) and adhere to original intent rather than inventing new behavior.
Audit Metadata