The Agent Skills Directory

[SAFE]: No malicious patterns or security risks were identified. The skill's behavior is entirely consistent with its documented purpose of project analysis and summarization. It does not involve network operations, sensitive file access (e.g., credentials), or the execution of external scripts.- [PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from a project's codebase and documentation, creating a surface for indirect prompt injection. This is a common characteristic of analysis tools and is documented here for completeness. * Ingestion points: Local project files, including code, documentation, and configuration files (SKILL.md). * Boundary markers: The instructions do not define specific delimiters to separate untrusted file content from the agent's internal instructions. * Capability inventory: The skill requires and utilizes file-reading capabilities to perform its analysis. * Sanitization: No explicit sanitization or validation of the ingested content is specified in the prompt.

learn-this