humaniser
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process, analyze, and rewrite arbitrary text content provided to it from external sources. \n
- Ingestion points: The skill ingests text for 'humanization' which can be read from files or provided via the agent's context. \n
- Boundary markers: The instructions do not define explicit delimiters or instructions to ignore any potential command-like patterns within the text being humanized. \n
- Capability inventory: The skill has access to Write and Edit tools, allowing it to modify the file system based on its analysis. \n
- Sanitization: There is no explicit sanitization or validation of the input text content before the agent processes it. \n- [EXTERNAL_DOWNLOADS]: The skill references the Wikipedia 'Signs of AI writing' guide as its core reference material.
Audit Metadata