Run a structured check on whether an image or video is AI-generated, digitally manipulated, or authentic-but-miscaptioned, and produce a sourced verdict with a confidence level. Use when a user forwards a dramatic war or news photo or clip on WhatsApp or Telegram and asks if it is real, when a journalist or community moderator needs a repeatable verification report before sharing or debunking, or when someone gets a suspicious image or voice claiming to be a known person. Combines cryptographic provenance (C2PA Content Credentials, SynthID, EXIF metadata), the agent's own visual inspection against an artifact checklist, and source tracing (reverse-image search, earliest-appearance, geolocation). This is a verifier, not a magic detector: it never claims certainty from one signal and says can't-verify when evidence is thin. Do NOT use for numeric or textual claim fact-checking (use israeli-fact-checker), for generating or removing deepfakes, or as court-admissible forensic certification.
Install with
Claude CodeCodexCursorGitHub CopilotGemini CLI
Supported by the Atlas install prompt. Skill-specific requirements vary.
Skill stats
Skills1CategorySecurityStars0
About this skill
Run a structured check on whether an image or video is AI-generated, digitally manipulated, or authentic-but-miscaptioned, and produce a sourced verdict with a confidence level. Use when a user forwards a dramatic war or news photo or clip on WhatsApp or Telegram and asks if it is real, when a journalist or community moderator needs a repeatable verification report before sharing or debunking, or when someone gets a suspicious image or voice claiming to be a known person. Combines cryptographic provenance (C2PA Content Credentials, SynthID, EXIF metadata), the agent's own visual inspection against an artifact checklist, and source tracing (reverse-image search, earliest-appearance, geolocation). This is a verifier, not a magic detector: it never claims certainty from one signal and says can't-verify when evidence is thin. Do NOT use for numeric or textual claim fact-checking (use israeli-fact-checker), for generating or removing deepfakes, or as court-admissible forensic certification.
Quick start
Copy the install prompt. Use the green button above this README.
Send it to your agent. Paste it into your coding agent’s chat and send.
Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.
Run a structured check on whether an image or video is AI-generated, digitally manipulated, or authentic-but-miscaptioned, and produce a sourced verdict with a confidence level. Use when a user forwards a dramatic war or news photo or clip on WhatsApp or Telegram and asks if it is real, when a journalist or community moderator needs a repeatable verification report before sharing or debunking, or when someone gets a suspicious image or voice claiming to be a known person. Combines cryptographic provenance (C2PA Content Credentials, SynthID, EXIF metadata), the agent's own visual inspection against an artifact checklist, and source tracing (reverse-image search, earliest-appearance, geolocation). This is a verifier, not a magic detector: it never claims certainty from one signal and says can't-verify when evidence is thin. Do NOT use for numeric or textual claim fact-checking (use israeli-fact-checker), for generating or removing deepfakes, or as court-admissible forensic certification.
About this listing
Category
Security
Reported license
MIT
Listing language (estimated)
English
Review status
Not individually reviewed
Agent compatibility
Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLI