humanize
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to rewrite user-provided text, which introduces an ingestion surface for untrusted data. 1. Ingestion points: The agent processes text provided by the user. 2. Boundary markers: The skill does not utilize delimiters to isolate the input text from the instructions. 3. Capability inventory: The skill does not include any scripts or access to tools that would allow for network, file, or command execution. 4. Sanitization: Input data is not sanitized or validated for embedded instructions.
- [NO_CODE]: The skill consists entirely of natural language guidelines and includes no executable scripts, binaries, or dependencies.
Audit Metadata