The Agent Skills Directory

[SAFE]: No malicious patterns, hidden commands, or suspicious behaviors were identified in the skill instructions.
[COMMAND_EXECUTION]: The skill uses git diff main to retrieve changes from the current branch. This is a standard operation in development environments.
[DATA_EXPOSURE]: The skill reads file contents from the local repository to perform style matching. This data access is confined to the project's scope and does not involve exfiltration.
[PROMPT_INJECTION]: The skill analyzes external code content which acts as an indirect prompt injection surface. However, this is expected behavior for code maintenance utilities and poses no direct threat.
Ingestion points: reads git diff output and file contents in SKILL.md.
Boundary markers: absent.
Capability inventory: local file read and modification.
Sanitization: absent.

deslop