The Agent Skills Directory

[SAFE]: No malicious patterns were identified. The skill acts as a localized refactoring tool.
[COMMAND_EXECUTION]: The skill instructs the agent to run git diff --name-only to scope the analysis to relevant changed files. This is a standard and safe operation for a code quality assistant.
[PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it processes code changes that may contain attacker-controlled comments.
Ingestion points: Reads files identified through git diff output as described in SKILL.md.
Boundary markers: Absent; the skill does not wrap the analyzed code in specific security delimiters.
Capability inventory: The agent has access to run_shell_command and replace to perform its tasks.
Sanitization: None; the skill relies on the underlying LLM's safety filters to distinguish code logic from instructions embedded in comments.

simplify