The Agent Skills Directory

[SAFE]: The skill's instructions and methodology are focused entirely on static code analysis for performance issues such as N+1 queries and algorithmic complexity. It operates in an advisory-only mode and explicitly states that it does not edit code.
[SAFE]: No hardcoded credentials, sensitive file path access, or unauthorized network operations were found in the instructions or the accompanying files.
[SAFE]: The included Node.js script scripts/checklist.mjs is a benign utility that prints a JSON-formatted checklist of the skill's methodology. It does not perform any sensitive system calls or network requests.
[PROMPT_INJECTION]: The skill processes untrusted code diffs, creating a surface for indirect prompt injection.
Ingestion points: Untrusted refactor diffs are processed as the primary data source (noted in SKILL.md and method.md).
Boundary markers: The skill does not define specific delimiters or instructions to the agent to ignore potentially malicious content or instructions embedded within the code diffs.
Capability inventory: The skill is limited to generating text reports based on templates; it does not utilize tools for file system modification, command execution, or network access.
Sanitization: There is no evidence of sanitization or filtering of the input code diffs before they are presented to the agent's context.

refactor-performance