content-humanizer
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill operates entirely on local files and user-provided text. It does not access sensitive system paths, environment variables, or hardcoded credentials.
- [SAFE]: The execution of the local script
scripts/humanizer_scorer.pyis safe as the script only performs static analysis of text using regex and does not utilize any dangerous functions or network capabilities. - [PROMPT_INJECTION]: Analysis of the indirect prompt injection surface identifies the following factors:
- Ingestion points: Untrusted data enters the agent context through the "content" provided by the user for humanization in
SKILL.md. - Boundary markers: The skill does not explicitly define delimiters or "ignore instructions" warnings for the processed text.
- Capability inventory: Capabilities are limited to reading local files (
marketing-context.md) and executing the provided local Python scoring script. - Sanitization: No explicit sanitization or escaping of input content is mentioned.
- Risk assessment: The lack of destructive capabilities or network access renders this surface safe for its intended purpose.
Audit Metadata