The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or unauthorized data access were detected. The skill promotes secure practices by instructing the agent to exclude secrets from tutorial examples and to verify instructions using safe checks available within the authorized environment.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data (repositories, entrypoints, and configuration files) to generate documentation. While this creates a surface for indirect prompt injection from malicious source content, the risk is inherent to the skill's core function of analyzing third-party codebases, and the instructions prioritize verification against authoritative documentation.

demo-to-tutorial