humanizer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [Prompt Injection / Indirect Prompt Injection] (LOW): The skill is designed to process and rewrite arbitrary user-provided text. This inherently creates a surface for indirect prompt injection where the input text could contain malicious instructions designed to hijack the agent's behavior.
- Ingestion points: User-provided text strings passed to the 'humanize' command.
- Boundary markers: The documentation does not specify the use of delimiters or 'ignore instructions' markers for the input text.
- Capability inventory: Text transformation and output generation.
- Sanitization: No sanitization or validation logic is described in the README.
- [No Code] (SAFE): The provided skill consists solely of a README.md file. No executable code, scripts, or package manifest files were found in the provided content.
Audit Metadata