changde-dialect

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses a Python script (scripts/dialect_hook.py) as a platform hook to manage state and inject system prompts. Analysis of the code shows it only performs safe file operations within its own skill directory to track if the dialect mode is enabled.
  • [DATA_EXPOSURE]: The glossary in references/glossary.md contains cultural references to historical folk magic (e.g., 'Iron Bull Water', 'Point Striking') and slang. These are documented as linguistic entries and do not represent executable code or sensitive data exfiltration.
  • [PROMPT_INJECTION]: The skill includes instructions to override the agent's persona to speak a dialect. This is the core intended functionality of the skill and does not attempt to bypass safety filters or ignore system-level constraints.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 04:29 AM
Security Audit — agent-trust-hub — changde-dialect