bad-faith-rhetoric-detector

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: No security vulnerabilities or malicious patterns were identified. The skill is composed entirely of Markdown documentation designed to guide an agent's reasoning process.
  • [NO_CODE]: The skill does not include any scripts, source code, binary executables, or package manifests. All logic is expressed through natural language instructions and examples.
  • [SAFE]: The instructions include robust 'Failure Modes' and 'Quality Gates' that act as internal guardrails, instructing the agent to avoid confirmation bias, psychological diagnoses, and the weaponization of its analysis.
  • [SAFE]: The documentation was scanned for obfuscation (Base64, hex encoding, zero-width characters) and prompt injection attempts; all content is transparent and consistent with the stated purpose of rhetoric analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 09:48 PM
Security Audit — agent-trust-hub — bad-faith-rhetoric-detector