humanizer
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and rewrite untrusted user-provided text. This creates a surface for indirect prompt injection where an attacker could embed instructions within the text meant for humanization.
- Ingestion points: User-provided text and writing samples used for style matching.
- Boundary markers: The skill does not define specific delimiters to isolate user content from system instructions.
- Capability inventory: The agent is instructed to rewrite prose and can perform file-writing operations if a target file is specified by the user.
- Sanitization: The instructions include constraints to "Keep code blocks, YAML metadata, data, and link targets unchanged," which serves as a protective measure against malicious content embedded in non-prose formats.
Audit Metadata