Skip to content
Get packs

CTF Stego Media Analysis

Guides an agent through hunting hidden data in images, audio, video and documents during CTF-style sandbox work.

Source Download skill
Repository
zhaoxuya520/reverse-skill
Stars
43,969
Licence
MIT
Files
3 files

What it does

This skill gives an AI agent a structured checklist for finding hidden payloads inside media files, such as data stored in image transparency or palette channels, least-significant bits, appended trailers, metadata, thumbnails, audio spectrograms, or video frames. Once installed, the agent inspects file structure first, ranks likely hiding places by evidence, and keeps each extraction step reproducible instead of guessing. It is designed as a sub-skill that only activates after a parent sandbox orchestrator skill has set up the context, and it replies in Simplified Chinese by default.

Great for

  • Players of capture-the-flag (CTF) security competitions working on steganography challenges
  • Security students learning how hidden data is embedded and recovered in media files
  • Security researchers reviewing suspicious files in an isolated sandbox

Skip it if

  • Hiding or exfiltrating data in files for evasion or malicious purposes, since the skill is oriented to recovering payloads in a controlled competition setting
  • Analysing real user media on production systems without authorisation, because it encourages running extraction tools against files of unknown origin
  • Pure cryptography problems, which the skill itself says should be handed to a separate crypto skill

Try asking

  • “Check this PNG for hidden data in its alpha channel, palette order or LSBs and show me the evidence for each channel”
  • “Look for an appended archive or trailer after the end of this JPEG and report the offsets”
  • “Inspect this WAV file's spectrogram and metadata for a hidden message and preserve each intermediate extraction”
  • “Examine this MP4's frame order and container indexes for a hidden payload, then stop once it is reproduced”
Step-by-step guide: how to use CTF Stego Media AnalysisInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 3 original files, the MIT licence and an attribution note.

    competition-stego-media.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip competition-stego-media.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip competition-stego-media.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Install and use it together with ctf-sandbox-orchestrator, otherwise the skill tells the agent to return to the orchestrator first
  • Run analysis on copies of files inside an isolated sandbox, since the agent may execute extraction tools on untrusted media
  • Ask for a written evidence trail (offsets, commands, intermediate files) because the skill is built around reproducibility

What's inside

  • agents/openai.yaml
  • references/stego-media.md
  • SKILL.md

Redistributed unmodified from zhaoxuya520/reverse-skill under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.