The Agent Skills Directory

[SAFE]: The skill's primary function is to perform a performance audit by scanning source code for patterns like N+1 queries, missing indexes, and memory inefficiencies. It uses standard tools such as Grep, Read, and Glob to examine files within the project environment.- [SAFE]: No remote code execution or external data exfiltration patterns were detected. The skill references local scripts and configuration files (e.g., scripts/complexity_scorer.py and ../codeprobe/shared-preamble.md) which is consistent with its role as a modular sub-skill.- [SAFE]: The usage of the Bash tool is restricted to executing local analysis scripts and does not involve downloading or running untrusted content from the internet.- [PROMPT_INJECTION]: The skill ingests untrusted project source code as part of its auditing process, creating a potential surface for indirect prompt injection. However, given its primary purpose as an auditor and the lack of autonomous dangerous capabilities, this risk is considered minimal and inherent to the tool's function.
Ingestion points: Reads source code files via Read, Grep, and Glob tools.
Boundary markers: No explicit markers are defined to separate code content from instructions.
Capability inventory: Tools for file reading and local bash execution.
Sanitization: No specific sanitization of the analyzed code is mentioned.

codeprobe-performance