The Agent Skills Directory

[SAFE]: The skill functions as a meta-instruction guide, helping users audit and adapt skill assumptions (tools, cadence, process) to their own environment. No malicious instructions, prompt injections, or data exfiltration patterns were detected.
[NO_CODE]: The skill consists entirely of markdown instructions and YAML metadata. It does not contain any executable scripts (Python, Node.js, Shell), nor does it request access to any tools via allowed-tools or perform network requests.
[INDIRECT_PROMPT_INJECTION]: While the skill involves processing and editing existing skills (untrusted data), it is a documentation framework for the user to follow manually. It does not automate the execution of instructions found within those skills.

skill-customizer