skills/leandrocfe/skills/ai-or-not/Gen Agent Trust Hub

ai-or-not

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructs the agent to analyze external content for AI indicators using a structured methodology involving context, origin, and specific technical signals.
  • [SAFE]: The skill provides detailed heuristics in SIGNALS.md for evaluating various media types (Text, Image, Video, Audio) for AI artifacts (e.g., anatomy errors, LLM linguistic patterns, audio inconsistencies).
  • [SAFE]: The skill uses appropriate tools for its purpose, such as exiftool and ffprobe, to inspect file metadata and media characteristics.
  • [SAFE]: The agent is explicitly instructed not to rely on unreliable automated AI detectors and to prioritize verifiable evidence over impressions.
  • [SAFE]: The skill is authored by 'leandrocfe' and does not involve external downloads, credential handling, or dangerous command execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 01:53 PM
Security Audit — agent-trust-hub — ai-or-not