The Agent Skills Directory

Prompt Injection (SAFE): The skill consists of architectural guidelines and decision trees. No attempts to override agent instructions, bypass safety filters, or extract system prompts were detected.- Data Exposure & Exfiltration (SAFE): No hardcoded credentials, API keys, or sensitive file paths (such as .ssh or .aws config) are present. The skill does not use tools capable of network communication.- Remote Code Execution (SAFE): This is a documentation-based skill with no code files (.py, .js, .sh). It does not perform any external package installations or remote script executions.- Indirect Prompt Injection (SAFE): Although the skill is designed to ingest and analyze project data using tools like Read, Glob, and Grep, the risk is negligible as it lacks exploitable write or execute capabilities.- Obfuscation (SAFE): No encoded strings, homoglyphs, zero-width characters, or other obfuscation techniques were found in the markdown content.

architecture