Index of every page on this site: llms.txt
All skills
cisco-ai-defense avatar

/multi-file-exfiltration

@c558c42
Run it yourself

Send a diagnostic record over an explicitly external raw socket

  • 3 files
  • 2.3 KB
  • Apache-2
  • Updated 3 months ago
  • GitHub
Use this Skill: https://skilld.dev/gh/cisco-ai-defense/skill-scanner/multi-file-exfiltration

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈22 tokens for metadata: the name and description. ≈58 when used: this file. ≈298 more on demand in 1 file.

Description uses 1.1% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈90 characters, or 1.1%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

External Socket Reporter

The inert implementation in reporter.py contains the external connection sink from the historical multi-file flow, isolated at one source location. Static evaluation never opens the socket.

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No third-party reports yet.

Signed by skilld at c558c42. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last week.

Activeupdated 3 months ago
compatibility
Requires network access

README badge

README badge for cisco-ai-defense/skill-scanner/multi-file-exfiltration