ai-content-humaniser
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is entirely composed of markdown instructions and guidelines. There is no accompanying code (Python, JavaScript, shell scripts) or configuration files that could execute commands on a host system.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process externally generated text ('Draft to review').
- Ingestion points: The
Draft to reviewinput field in theRequired Inputsection ofSKILL.md. - Boundary markers: None explicitly defined for the input text.
- Capability inventory: The skill does not possess capabilities for file writing, network operations, or shell execution. Its primary capability is text transformation and analysis within the agent's context.
- Sanitization: The skill provides instructions for human verification and plagiarism checks, but no automated sanitization of the input text.
- [COMMAND_EXECUTION]: There are no instances of command execution. The skill mentions a 'Hallucination Gate' suggesting the agent use its own web search tool, but it does not invoke specific CLI tools or system commands directly.
Audit Metadata