The Agent Skills Directory

[SAFE]: The skill is composed entirely of Markdown documentation and reference materials. It contains no executable scripts (Python, JavaScript, or Shell) and does not define any automated tools.
[EXTERNAL_DOWNLOADS]: The skill includes links to official U.S. government domains, such as bis.gov and trade.gov, which provide access to the Consolidated Screening List and the interactive Commerce Control List. These are recognized as safe, well-known government services.
[NO_CODE]: There are no software components or installation procedures associated with this skill, eliminating risks related to remote code execution or privilege escalation.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied export compliance scenarios to provide classification advice. While an ingestion point exists (user queries), the skill possesses zero capabilities for file access, network operations, or command execution, neutralizing any injection risk.
Ingestion points: User-supplied technical data and export scenarios in SKILL.md.
Boundary markers: None identified.
Capability inventory: No file system access, no network operations, no subprocess calls, and no dynamic execution (eval/exec) across all files.
Sanitization: Not applicable as the skill does not use executable logic to process inputs.

ear