skills/connorads/dotfiles/humanizer/Gen Agent Trust Hub

humanizer

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted user-supplied text and possesses permissions for file-system modification through tools like Write and Edit. The absence of boundary markers or explicit instructions to disregard embedded commands within the input text creates a surface for indirect prompt injection, where malicious input could potentially influence agent actions such as modifying unintended files.\n
  • Ingestion points: User-provided text for humanization as defined in the instructions within SKILL.md.\n
  • Boundary markers: There are no delimiters or "ignore" instructions present in the prompt logic to isolate the processed data from the agent's operational instructions.\n
  • Capability inventory: The skill is configured with access to Read, Write, Edit, Grep, Glob, and AskUserQuestion tools.\n
  • Sanitization: No validation, escaping, or filtering is performed on the text to be processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 08:01 PM