skills/csfuwwc/md-skills/humanizer-zh/Gen Agent Trust Hub

humanizer-zh

Pass

Audited by Gen Agent Trust Hub on Aug 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and transform external text provided by users. Because the agent is granted Read, Write, and Edit tools, it presents an attack surface where instructions embedded within the text to be processed could potentially influence the agent's behavior.
  • Ingestion points: Untrusted text provided for 'humanization' (SKILL.md).
  • Boundary markers: The instructions do not define explicit delimiters or 'ignore' instructions for the input data.
  • Capability inventory: The skill utilizes Read, Write, and Edit tools to interact with the file system.
  • Sanitization: There is no evidence of automated sanitization or filtering of the input text to prevent instruction injection.
  • [SAFE]: The skill references writing guidelines from Wikipedia's 'WikiProject AI Cleanup'. This is a well-known and trusted informational resource.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 29, 2026, 12:00 PM
Security Audit — agent-trust-hub — humanizer-zh