The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions and structural guidelines for the AI agent to follow. There are no executable scripts, configuration files, or external dependencies included.
[INDIRECT_PROMPT_INJECTION]: The skill instructions involve analyzing external creator content. This creates a data ingestion surface where untrusted data (the examples provided to the agent) enters the context. However, because the skill has no functional capabilities (no tools, network access, or file system operations), the risk of exploitation is negligible. Evidence chain: 1. Ingestion points: Content examples (SKILL.md); 2. Boundary markers: Absent; 3. Capability inventory: None; 4. Sanitization: Absent.

voice-matching