The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were identified in the skill configuration.
[NO_CODE]: The skill does not include any executable scripts or binaries, relying entirely on platform-provided tools and AI-driven analysis.
[PROMPT_INJECTION]: While the skill analyzes external code, which is a potential surface for indirect prompt injection, this behavior is inherent to its primary function and no malicious intent was identified.
Ingestion points: Code content is read from the local file system using the Read and Grep tools.
Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands in the analyzed code.
Capability inventory: The skill is limited to Read, Glob, Grep, and Task tools for searching, reading, and orchestrating sub-agent tasks.
Sanitization: No pre-processing or sanitization of ingested file content is performed before analysis.

detect-over-engineering