humanize
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [NO_CODE] (SAFE): The skill is comprised entirely of Markdown files and reference rules. It does not include any executable scripts, which eliminates code-based attack vectors like RCE or command injection.
- [PROMPT_INJECTION] (SAFE): The skill processes user-supplied text, which is an inherent surface for indirect prompt injection. The risk is categorized as SAFE because the skill lacks any capabilities (network, file system, or shell) that could be exploited. 1. Ingestion points: User input text. 2. Boundary markers: Not specified. 3. Capability inventory: None. 4. Sanitization: Absent.
- [SAFE] (SAFE): No hardcoded credentials, obfuscation, or persistence mechanisms were found. The use of the environment variable WRITING_STYLE_GUIDE_PATH is a standard configuration pattern without exfiltration risk.
Audit Metadata