Skip to content
SkillModel-led494 tokens in use

competition-stego-media

A CTF sandbox workflow for finding hidden data in images, audio, video and documents by ranking evidence-backed channels.

44,996 stars on the repository MIT Licensezhaoxuya520/reverse-skill · CTF-Sandbox-Orchestrator/competition-stego-media
git clone https://github.com/zhaoxuya520/reverse-skill.git
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing competition-stego-media costs

101tokens idle
494tokens in use
708tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter12/15
  • Structure23/25
  • Examples3/15
  • Output12/15
  • Size15/15
  • Resources7/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity96
  • Maintenance72
  • Community72
  • Maturity28
  • Momentum40

This skill is a downstream specialization of the ctf-sandbox-orchestrator skill. It covers steganography challenges in image, audio, video, document and container files: metadata, thumbnails, appended trailers, alpha and palette channels, LSBs and transcoding artifacts.

The agent confirms the real container structure first, ranks candidate channels by evidence, keeps each extracted layer as a separate file and stops when the hidden payload is reproduced. Replies are in Simplified Chinese unless English is requested.

What You Get

  • A first-pass checklist for magic bytes, chunk layout, metadata, thumbnails and trailers
  • A ranked list of candidate channels: alpha, palette, LSB, frame deltas, document streams and transform residue
  • A rule to keep every extracted stage as its own file with its transform recorded
  • A hand-off pointer to the broader crypto skill when the extracted data is ciphertext

Common Use Cases

  • Looking for appended archives or trailers in an image from a CTF challenge
  • Checking alpha, palette and LSB channels of a sandbox image
  • Documenting the transform chain that produced a hidden payload

What Makes It Unique

It favors evidence-driven checks of structure and metadata before signal-domain work and avoids blind brute force. It separates a channel hit from artifact recovery, and it runs only after the orchestrator skill has set sandbox assumptions.

Under The Hood

The skill is instruction text only: a SKILL.md, one reference checklist and an agent config file that disables implicit invocation. It ships no scripts and does not itself fetch pages, call APIs, run commands or write files. The agent inspects media with tools the user already has, and keeps extracted layers as separate files.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers