The Agent Skills Directory

[SAFE]: No security issues, malicious patterns, or dangerous command executions were detected. The skill provides purely instructional content for text transformation.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted Finnish text provided by the user. 1. Ingestion point: User-provided text for 'humanization' as described in SKILL.md. 2. Boundary markers: None explicitly defined for input text. 3. Capability inventory: The skill does not request or use any tools for network access, file system modification, or shell execution. 4. Sanitization: The instructions mandate that the agent must preserve the original factual content and technical terminology, which limits the potential for following embedded malicious instructions. Given the lack of executable capabilities, this ingestion surface is considered safe.

finnish-humanizer