The Agent Skills Directory

[SAFE]: The skill's instructions in SKILL.md and the reference documentation follow standard technical workflow patterns. There are no attempts to override agent behavior, bypass safety guidelines, or extract system prompts.
[SAFE]: No network operations, data exfiltration patterns, or hardcoded credentials were detected. The Python scripts (new-adr.py, lint-adr.py) interact only with local Markdown files in the user-specified directory (defaulting to docs/decisions). External links in the documentation point to legitimate MADR project resources on GitHub and official domains.
[SAFE]: No obfuscation techniques, such as Base64-encoded commands, zero-width characters, or homoglyph substitutions, were found in any of the analyzed files.
[SAFE]: The helper scripts use standard Python libraries (argparse, re, pathlib, datetime). There is no evidence of remote code execution, piped shell commands, or installation of unverifiable dependencies.
[SAFE]: The skill does not attempt to gain elevated privileges (sudo, chmod 777) or establish persistence on the system. All file operations are standard for a document management tool.
[SAFE]: No dynamic execution patterns, unsafe deserialization (e.g., pickle), or runtime code generation from untrusted sources were identified.

madr-adr