The Agent Skills Directory

[NO_CODE]: The skill is entirely informational, containing markdown frameworks for legal and compliance expertise without any associated scripts or executable components.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data such as contracts, demand letters, and regulatory queries, which creates a theoretical attack surface.
Ingestion points: User-provided contract text and legal inquiries as described in the "Contract Management" and "Litigation Management" sections of SKILL.md and the intake stage of references/legal-compliance-excellence-skill.md.
Boundary markers: None identified.
Capability inventory: None. The skill does not invoke any shell tools, file-writing utilities, or network operations across any of the provided files.
Sanitization: None identified.
[SAFE]: Analysis of all threat categories, including prompt injection, data exfiltration, obfuscation, and remote code execution, yielded no findings. The skill's content is consistent with its stated purpose of providing legal and compliance advisory support.

legal-compliance