The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were detected. The skill's logic is entirely focused on Git repository recovery and management.
[COMMAND_EXECUTION]: The skill utilizes standard Git CLI commands (e.g., status, log, reflog, reset, clean). It includes robust guardrails requiring explicit user confirmation before executing any destructive or broad operations that could lead to work loss.
[DATA_EXFILTRATION]: No network operations or patterns associated with data exfiltration were found. The skill operates exclusively on the local Git repository state.
[PROMPT_INJECTION]: No attempts to bypass safety filters or override agent behavior were identified. The instructions are declarative and strictly scoped to Git workflows.
[CREDENTIALS_UNSAFE]: The skill does not contain or request hardcoded credentials. It provides safe procedures for removing sensitive data from Git history, specifically instructing the agent to avoid creating Git-based backups (like stashes or patches) that might inadvertently preserve confidential blobs.

undo-recover