The Agent Skills Directory

[SAFE]: No security issues were detected. The skill contains text-based instructions for the agent to assist users in documenting AI disclosure practices and compliance with regulations like the EU AI Act.
[NO_CODE]: The skill does not include any scripts, shell commands, or external dependencies. It operates entirely through natural language interaction.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied information regarding company AI surfaces and existing policy fragments.
Ingestion points: The Required Inputs section in SKILL.md specifies that the agent should ask for details on AI output locations, markets served, and existing policy fragments.
Boundary markers: No specific delimiters are defined for these inputs.
Capability inventory: The skill lacks any file system access, network operations, or command execution capabilities.
Sanitization: Not applicable as there are no executable capabilities to exploit.

ai-disclosure-policy