The Agent Skills Directory

[SAFE]: The skill's primary function is a security feature, scanning analysis outputs for PII (such as SSNs via regex) and small cell counts to prevent accidental data disclosure.
[SAFE]: No prompt injection or behavior override patterns were detected; the instructions are strictly focused on the diagnostic workflow.
[SAFE]: The skill uses local file system tools (Read, Grep, Glob, Bash, Write) to perform its analysis and does not request network access or interact with remote domains.
[SAFE]: The disable-model-invocation: true flag in the frontmatter provides an additional layer of safety by restricting the agent's ability to invoke other models during execution.
[SAFE]: No obfuscation (Base64, zero-width characters) or persistence mechanisms were found in the instructions.

disclosure-check