The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional markdown and reference files designed to guide an AI agent in generating unit tests and breaking code dependencies. No executable code, remote downloads, or suspicious commands were detected.
[NO_CODE]: This skill contains no executable scripts or binaries, consisting purely of documentation and configuration for the AI agent.
[SAFE]: Indirect prompt injection surface is documented for completeness. The skill instructs the agent to analyze project configuration files to determine the development environment. This creates a surface for indirect prompt injection if those files contain malicious instructions. However, the risk is minimal as the agent uses this data solely for context detection. 1. Ingestion points: Project configuration files such as pom.xml and package.json. 2. Boundary markers: None specified. 3. Capability inventory: Code generation and architectural advice. 4. Sanitization: None specified.

test-legacy