rhetorical-analyst

Pass

Audited by Gen Agent Trust Hub on Apr 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a set of analytical instructions for an AI agent to perform rhetorical analysis. It defines a multi-dimensional framework (Persuasion, Rhetoric, Logic) and provides specific workflows for mapping moves and identifying logical gaps.
  • [SAFE]: It references 'InfraNodus MCP tools' for structural text analysis (topical clustering, gap detection). These are handled as standard tool invocations within the agent's environment to process user-provided text.
  • [SAFE]: The instructions emphasize analytical neutrality, symmetry, and 'understanding is not endorsing', which align with safety guidelines regarding unbiased analysis of controversial topics.
  • [SAFE]: No malicious patterns such as prompt injection, data exfiltration, or unauthorized command execution were detected. The skill's complexity is entirely dedicated to its stated purpose of argument analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 4, 2026, 11:13 PM
Security Audit — agent-trust-hub — rhetorical-analyst