humanizer-pl

Pass

Audited by Gen Agent Trust Hub on Aug 11, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to ingest and process external Polish text for 'humanization,' which inherently creates a surface for indirect prompt injection. Maliciously crafted input text could attempt to bypass the skill's editing logic to influence the agent's behavior. \n
  • Ingestion points: The skill utilizes the Read tool to ingest content from files and AskUserQuestion to receive text from the user. \n
  • Boundary markers: The instructions do not define explicit delimiters (such as XML tags or specific quotation markers) or include 'ignore embedded instructions' warnings for the text being processed. \n
  • Capability inventory: The skill is granted Write and Edit permissions, allowing the agent to modify the file system based on potentially manipulated input. \n
  • Sanitization: The skill lacks defined methods for sanitizing, escaping, or validating the input text before the agent processes and acts upon it.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 11, 2026, 07:15 PM
Security Audit — agent-trust-hub — humanizer-pl