The Agent Skills Directory

[SAFE]: The skill is a static analysis tool that audits local codebases for adherence to framework-specific best practices. It correctly uses internal configuration files and reference guides to perform its tasks.
[COMMAND_EXECUTION]: The skill utilizes the Bash tool in conjunction with Grep and Read to identify code patterns. This usage is confined to the local project environment and aligns with the tool's primary function.
[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it ingests untrusted source code from the project environment for analysis.
Ingestion points: Analyzes project source files and configuration files (e.g., composer.json, package.json, requirements.txt).
Boundary markers: No explicit delimiters or boundary markers are defined to isolate the ingested code content.
Capability inventory: The agent is granted access to Bash, Read, Grep, and Glob tools.
Sanitization: No specific sanitization or filtering logic is provided for the content of the analyzed files.

rc-codeprobe-framework