The Agent Skills Directory

[SAFE]: No malicious patterns or security risks were identified. The skill focuses on Git operations with explicit safety constraints and evidence-based decision rules.
[SAFE]: Analysis of indirect prompt injection surface: The skill ingests untrusted data from repository files, commit messages, and issue text. It includes specific boundary markers requiring the agent to treat this content as data rather than instructions. Capabilities are limited to Git index operations and conflict resolution, with sanitization performed through mandatory semantic review and verification tests.

resolve-conflicts