The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional Markdown documentation and JSON evaluation test cases. It does not contain any executable scripts, command-line operations, or network requests. No malicious patterns were detected across any analyzed threat categories.- [NO_CODE]: There is no functional code (Python, JavaScript, or shell scripts) included in the skill files. All logic is provided through natural language instructions for the AI agent, making it a low-risk instructional resource.- [INDIRECT_PROMPT_INJECTION]: The skill utilizes a structured interview process to gather event requirements from users. While this represents a surface for ingesting untrusted data, the skill lacks any capabilities (such as file writes, network operations, or subprocess execution) that could be exploited via prompt injection. 1. Ingestion points: User responses to the 10-question interview defined in SKILL.md. 2. Boundary markers: None explicitly defined. 3. Capability inventory: None (no code or tools). 4. Sanitization: No sanitization of user input is specified.

event-hospitality