skills/sarthib7/agentsmith/humanizer/Gen Agent Trust Hub

humanizer

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill demonstrates an indirect prompt injection surface.
  • Ingestion points: Untrusted data is ingested via user-pasted text or file contents during invocation, as specified in the 'Invocation Modes' section of SKILL.md.
  • Boundary markers: The instructions lack explicit delimiters or safety warnings to distinguish between instructions and processed data.
  • Capability inventory: The 'File mode' in SKILL.md grants the agent authority to read files and 'rewrite the file in place', providing a mechanism for input-driven file modification.
  • Sanitization: There are no documented procedures for escaping, validating, or filtering the external content before processing.
  • [EXTERNAL_DOWNLOADS]: The skill documentation in README.md references installation via git clone from GitHub and the npx skills CLI tool. These installation methods utilize well-known services.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 11:05 AM
Security Audit — agent-trust-hub — humanizer