agentsclimarketplace

Bellingcat image video

Skill CasualSecurityInc/Bellingcat-OSINT-Toolkit/skills/bellingcat-image-video

Curated AI agent skills for open-source intelligence investigations — 320+ tools from Bellingcat's Toolkit across 12 categories: geolocation, image/video forensics, social media, people search, transport tracking, conflict monitoring, data analysis & more.

Install
npx -y skills add CasualSecurityInc/Bellingcat-OSINT-Toolkit --skill bellingcat-image-video

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

3 things to look at

  • 25 days oldThe repository was created 25 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Verify and analyze photos, videos, and images. Reverse image search, extract EXIF metadata, detect deepfakes/GAN images, perform facial recognition, and analyze video content. Use when the user shares an image, photo, screenshot, or video and needs to verify authenticity, find the source, or identify people/objects, even if they don't mention "OSINT."

SKILL.md

9.2 KB, ~2.1k tokens by cl100k_base, as published. Nobody here has run it

Bellingcat Image & Video Investigation Tools

Tools for verifying, analyzing, and extracting information from photos and videos. Covers reverse image search, metadata extraction, facial recognition, and video forensics.

Choosing Tools

  • Use reverse search to investigate provenance, metadata tools for origin clues, and forensic tools to assess possible manipulation.
  • Treat facial-recognition results as leads, not identification; corroborate with independent evidence and consider privacy impacts.

Tools

Reverse Image Search

ToolBest forCostDescriptionGuide
Google LensAn image recognition tool that can be used to identify locations or objects in photographs.FreeGoogle Lens is an image recognition tool that can be used to identify locations or objects in photographs.Details
InVIDA toolkit that supports the verification of videos and images.FreeA toolkit that supports the verification of videos and images.Details
RootAboutReverse search images on the Internet ArchiveFreeReverse search images on the Internet ArchiveDetails
Search by ImageA browser extension to reverse search an image on multiple search engines.FreeA browser extension to reverse search an image on multiple search engines.Details
TinEyeA search engine that allows the user to search using images (reverse image search).FreeTinEye is a search engine that allows the user to search using images (reverse image search).Details

Facial Recognition

ToolBest forCostDescriptionGuide
Amazon RekognitionCheck how similar two faces areFreeCheck how similar two faces are
Azure AI Video IndexerAI video tool for facial detection and other types of insights.PaidAI video tool for facial detection and other types of insights.Details
Face Comparison by ToolPieCompares two human face photos to determine similarity.FreeCompares two human face photos to determine similarity.Details
FaceCheck.IDA facial recognition search engine that tries to find photos of people that look similar…PaidA facial recognition search engine that tries to find photos of people that look similar to a person of interest.Details
PimEyesAn AI-powered facial recognition reverse image search tool.PaidAn AI-powered facial recognition reverse image search tool.Details
Search4FacesUpload the picture of a face and find pictures of similar looking people on VKontakte,…FreeUpload the picture of a face and find pictures of similar looking people on VKontakte, Odnoklassniki, TikTok and Club...Details

Metadata & EXIF

ToolBest forCostDescriptionGuide
ExifPurgeEXIF Purge is a small portable application to remove EXIF metadata from multiple images at…FreeEXIF Purge is a small portable application to remove EXIF metadata from multiple images at once. With the click of a ...
ForensicallyA collection of web-based image forensics tools.FreeA collection of web-based image forensics tools. Can identify fake or doctored images.Details
FotoForensicsImage forensics tool.FreeImage forensics tool.
InVIDA toolkit that supports the verification of videos and images.FreeA toolkit that supports the verification of videos and images.Details
IrfanviewWindows-based software to extract metadata.FreeWindows-based software to extract metadata.
JimplOnline EXIF data viewerFreeOnline EXIF data viewer
metadata2goCheck metadata for both photos and videos online.FreeCheck metadata for both photos and videos online.
Reveal Image Verification AssistantForensic providing eight filters to detect still images alterations.FreeForensic providing eight filters to detect still images alterations. Web-based image tool. Also available within InVI...
xIFrA Firefox add-on for extracting EXIF metadata by right-clicking an image.FreeA Firefox add-on for extracting EXIF metadata by right-clicking an image.Details

Image Misc

ToolBest forCostDescriptionGuide
AmIRealGithub - GAN detector detects if faces were generated by ThisPersonDoesNotExistFreeGithub - GAN detector detects if faces were generated by ThisPersonDoesNotExist
AutoStitchAutostitch is a free tool for seamlessly combining multiple photos into a single panoramic…FreeAutostitch is a free tool for seamlessly combining multiple photos into a single panoramic image, making it ideal for...Details
Cleanup.PicturesWeb tool for quickly removing objects from an image.FreeWeb tool for quickly removing objects from an image.
fdupesGithub - Locating exact matches of duplicate files.FreeGithub - Locating exact matches of duplicate files.
ForensicallyA collection of web-based image forensics tools.FreeA collection of web-based image forensics tools. Can identify fake or doctored images.Details
HuginA free and open-source panorama photo stitching and HDR (High Dynamic Range imaging)…FreeHugin is a free and open-source panorama photo stitching and HDR (High Dynamic Range imaging) merging software that h...Details
InVIDA toolkit that supports the verification of videos and images.FreeA toolkit that supports the verification of videos and images.Details
IPVM CalculatorTool for simulating camera views (for geolocations).FreeTool for simulating camera views (for geolocations).
PureRefImage workspace; lets you arrange images in groups, organize them, etc.FreeImage workspace; lets you arrange images in groups, organize them, etc.

Investigation Tips

  • Start with reverse image search (Google Lens, TinEye) to find the earliest known appearance of an image
  • Extract EXIF metadata (Jimpl, metadata2go, xIFr) to find camera model, date, and GPS coordinates
  • Use Forensically for a suite of forensic filters to detect manipulation (clone detection, error level analysis)
  • For videos, use InVID to extract key frames for reverse image search and verify authenticity
  • PimEyes or FaceCheck.ID for facial recognition — be aware of ethical and privacy considerations
  • AmIReal detects GAN-generated faces; use before trusting facial recognition results

Gives 0 of the 12 instructions most video audio skills give in ~2.1k tokens

Counted across 621 of the 795 authors here whose files we hold, read 2026-08-06

  • read individual rule files for detailed explanationsin 21 of 621, across 9 files
  • Use WAV PCM 16kHz mono audio formatin 13 of 621, across 4 files
  • render final videoin 13 of 621, across 6 files
  • use this skill when dealing with Remotion codein 11 of 621, across 4 files
  • save generated audio to a WAV filein 11 of 621, across 4 files
  • handle conversion errors gracefullyin 10 of 621, across 6 files
  • add captions to videos alwaysin 10 of 621, across 4 files
  • generate music from text descriptions using MusicGenin 9 of 621, across 2 files
  • do not skip pipeline layersin 9 of 621, across 3 files
  • do not make one tool do everythingin 9 of 621, across 3 files
  • never ask the user to paste their full API keyin 9 of 621, across 3 files
  • use azure document intelligence for complex pdfsin 9 of 621, across 4 files

Said here and by no other author read

  • use reverse search to investigate provenance
  • use metadata tools for origin clues
  • use forensic tools to assess manipulation
  • treat facial recognition results as leads
  • corroborate leads with independent evidence
  • consider privacy impacts of facial recognition

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.