The Agent Skills Directory

[SAFE]: No malicious patterns or security risks were identified in the analysis of the skill's instructions and configuration.
[COMMAND_EXECUTION]: The skill uses the Bash tool for local code analysis tasks, which is appropriate for its stated purpose of auditing project source code for architectural patterns.
[PROMPT_INJECTION]: The skill processes external source code as data, creating a surface for potential indirect prompt injection. Ingestion points: The skill reads project files and technology stack metadata using the Read, Grep, and Glob tools. Boundary markers: No explicit delimiters or instruction-ignore blocks are defined in this file to separate code content from instructions. Capability inventory: The skill has access to Bash for shell execution and various file reading tools. Sanitization: No sanitization or validation logic for the ingested code content is specified in the instructions.

codeprobe-patterns