The Agent Skills Directory

[SAFE]: The skill implements a structured pedagogical framework for explaining concepts concisely. It enforces specific output slots, word counts, and evidence requirements.
[REMOTE_CODE_EXECUTION]: No remote code execution patterns were detected. The skill instructions focus on text processing and local/trusted file reading for citation purposes.
[DATA_EXFILTRATION]: No exfiltration patterns detected. Network access is restricted to fetching official documentation (e.g., Microsoft Docs) as cited in the evidence rules.
[PROMPT_INJECTION]: The skill uses clear instructions to govern its own output behavior and formatting, but does not contain patterns intended to bypass safety filters or override system instructions.
[EXTERNAL_DOWNLOADS]: The skill references standard, well-known documentation sources (Microsoft Docs) for information gathering, which is considered safe behavior.
[OBFUSCATION]: No obfuscated code, hidden URLs, or encoded payloads were found in SKILL.md or the reference files.
[CREDENTIALS_UNSAFE]: No hardcoded credentials or sensitive environment variable exposure patterns were found.
[PRIVILEGE_ESCALATION]: No attempts to acquire elevated permissions or modify system configurations were detected.
[PERSISTENCE]: No persistence mechanisms (e.g., shell profiles, cron jobs) were detected.
[DYNAMIC_CONTEXT_INJECTION]: The skill does not use dynamic shell execution syntax (!command) in its instructions.

feynman-explain