Binary Triage
CheckedBinary Triage swiftly analyzes data represented in binary format to prioritize and categorize information for rapid investigation & threat assessment.
Install on your platform
Showing Claude Code. One command installs this skill into any of the agents below.
- 1
Run this in your project
terminal$ npx skills add cyberkaida/reverse-engineering-assistant --skill binary-triage -a claude-code Uses the open-source
skillsCLI and needs Node.js. Add-gto install it for your user instead of this project.
What we know about this skill
Publisher
cyberkaida
Taken from the source listing. We haven't verified who controls this account.
Install target
Live repository
Not pinned. Installing fetches whatever the repository holds at the time you run the command.
Automated safety checks
This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.
Declares what it does: passed
SKILL.md parses and declares a name and a description.
SKILL.md exists, its frontmatter parses, and it declares a name and a description.
No undeclared network calls: passed
Makes no network calls.
Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.
No obfuscated payloads: passed
No encoded or obfuscated payloads.
No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.
No credential access: passed
Reads no keys, tokens, keychains or credential files.
Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.
No pipe-to-shell installers: passed
No pipe-to-shell or download-and-run installers.
No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.
Pinned to a commit: passed
Scanned cyberkaida/reverse-engineering-assistant at f603ba9833.
The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.
- Commit
- f603ba9833
- Scanned
- 1 file, 156 lines
About this skill
What it does
The binary-triage skill enables AI agents to analyze raw binary files and categorize them based on their structure, signatures, and content. It helps distinguish between executable code, data archives, encrypted blobs, or malformed files without requiring manual inspection.
When to use it
- Security Analysis: Quickly identify potential malware samples by classifying unknown file types before deep scanning.
- Data Cleanup: Sort mixed binary datasets in a repository to separate valid executables from corrupted or irrelevant data.
- Reverse Engineering Prep: Determine if a dumped memory image is an ELF, PE, or Mach-O format before attempting disassembly.
- Malware Hunting: Filter large collections of suspicious files to isolate those with specific binary characteristics.
Key capabilities
- Analyzes raw binary content for structural patterns and magic numbers.
- Classifies file types including executables, libraries, archives, and encrypted data.
- Detects malformed or truncated binary structures.
- Provides confidence scores for classification accuracy.
Example prompts
- "Run binary-triage on this suspicious file dump to determine if it is a valid ELF executable."
- "Categorize these 50 unknown binary files and list any that appear to be encrypted archives."
- "Analyze the provided memory dump and identify the underlying process format (PE vs. Mach-O)."
Tips & gotchas
Ensure the binary file is not actively malicious or contains sensitive data before passing it to an agent for analysis. This skill relies on static signatures; it may misclassify obfuscated or heavily packed binaries without additional context.