nudge-theory

Pass

Audited by Gen Agent Trust Hub on Aug 22, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves an educational and architectural purpose, providing guidelines for behavioral design based on established academic frameworks (EAST).
  • [DATA_EXPOSURE_AND_EXFILTRATION]: No sensitive data access or exfiltration patterns were detected. All external links point to legitimate vendor sites (deciqai.com), official GitHub repositories, or authoritative regulatory and academic sources (FTC, EU, Nature, Yale).
  • [PROMPT_INJECTION]: The skill uses a structured 'Adaptive Front Door' to guide users, including [WAIT] markers to control flow, which is a standard interactive design pattern and does not attempt to bypass safety filters or override system instructions.
  • [TRUSTED_SOURCES]: The skill references well-known and reputable sources including the UK Behavioural Insights Team, the FTC, and the Nobel Prize organization, all of which are documented neutrally.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 22, 2026, 08:15 AM
Security Audit — agent-trust-hub — nudge-theory