The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were identified. The skill is designed to perform static analysis on source code to identify architectural and framework-specific improvements.- [COMMAND_EXECUTION]: The skill is granted access to the Bash tool in its configuration. However, the provided instructions do not include any shell command execution or user-input interpolation into shells; the tool is primarily scoped for codebase analysis.- [DATA_EXFILTRATION]: The skill uses Read, Grep, and Glob tools to inspect project files such as composer.json, package.json, and source code modules. No network operations or external communication patterns were detected.- [PROMPT_INJECTION]: While the skill ingests untrusted codebase data, which is an inherent surface for indirect prompt injection, the instructions strictly define pattern-matching rules for framework conventions. The agent is directed to emit zero findings if no supported framework is detected, reducing the risk of executing instructions embedded in analyzed data.

codeprobe-framework