Skip to content
TrustedSkillsbeta
Back to all skills

Stealth

Listed
tapauth·vlatest·other

This "Stealth" skill minimizes your digital footprint by masking your activity, enhancing privacy and security during online interactions.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add tapauth/stealth --skill stealth -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

tapauth

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.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill failed 2 of 6 checks. A failure is not proof of bad intent; it means something in the code needs a human to look at it before you run it.

  • No undeclared network calls: failed

    Contacts 5 hosts that are neither well-known infrastructure nor declared in the skill's frontmatter: 2captcha.com, api.capsolver.com, httpbin.org, ipinfo.io, polymarket.com.

    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.

    Hosts contacted

    ipinfo.ioundeclaredapi.capsolver.comundeclared2captcha.comundeclaredpolymarket.comundeclaredhttpbin.orgundeclared

    What it found (3 of 13)

    • stealth/SKILL.md:23contacts ipinfo.io
      curl -s https://ipinfo.io/json | python3 -c "
    • stealth/SKILL.md:53contacts ipinfo.io
      curl -x http://USER:PASS@HOST:PORT -s https://ipinfo.io/json | python3 -c "
    • stealth/references/proxy-setup.md:35contacts ipinfo.io
      curl -x http://USERNAME:PASSWORD@HOST:PORT -s https://ipinfo.io/json

  • No pipe-to-shell installers: failed

    Runs code fetched at install time in 2 places.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

    What it found

    • stealth/SKILL.md:23remote script piped into an interpreter
      curl -s https://ipinfo.io/json | python3 -c "
    • stealth/SKILL.md:53remote script piped into an interpreter
      curl -x http://USER:PASS@HOST:PORT -s https://ipinfo.io/json | python3 -c "

  • 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 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.

  • Pinned to a commit: passed

    Scanned tapauth/stealth at da6cb5c0d9.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
da6cb5c0d9
Manifest
stealth/SKILL.md
Scanned
6 files, 742 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

The stealth skill allows AI agents to operate with reduced visibility and impact. It enables the agent to avoid detection during tasks, minimize unwanted attention, and execute actions discreetly. This is achieved by carefully managing communication patterns and interaction styles.

When to use it

  • Data Gathering: When collecting information from sensitive sources where overt querying could trigger alarms or restrictions.
  • Automated Reporting: To generate reports without disrupting ongoing processes or alerting individuals involved.
  • System Monitoring: For quietly observing system behavior and identifying anomalies without generating noise in logs.
  • Negotiation Support: To analyze communication patterns during negotiations and suggest subtle adjustments for improved outcomes.

Key capabilities

  • Reduced verbosity in communications
  • Mimicry of natural language patterns
  • Discreet data retrieval
  • Minimized interaction footprint

Example prompts

  • "Analyze this email thread and summarize the key decisions, but do so without alerting any participants."
  • "Monitor server logs for unusual activity, but avoid generating excessive log entries yourself."
  • "Draft a response to this customer complaint that is polite and helpful, while avoiding language that might escalate the situation."

Tips & gotchas

The effectiveness of stealth depends on careful prompt engineering. Overly aggressive attempts at concealment can be counterproductive and raise suspicion.