2Captcha CLI

Security checks across static analysis, malware telemetry, and agentic risk

Overview

This skill is transparent about what it does, but it is designed to help an agent bypass CAPTCHA protections and install an unpinned remote CLI.

Review this carefully before installing. It may be appropriate only for authorized testing or workflows you control; using it to bypass CAPTCHA protections on third-party sites can violate site rules and enable abuse. If you proceed, inspect and pin the remote CLI before installing, protect the 2Captcha API key, and avoid submitting sensitive page content.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Risk analysis

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

#
ASI02: Tool Misuse and Exploitation
High
What this means

An agent using this skill could help automate actions that websites intentionally block with CAPTCHA challenges.

Why it was flagged

The skill is explicitly framed for bypassing CAPTCHA protections, including account creation and form submission, which are common anti-abuse enforcement points.

Skill content
Use for bypassing captchas during web automation, account creation, or form submission.
Recommendation

Only use this in systems you own or are explicitly authorized to test; add explicit user confirmation and authorized-use limits before solving or injecting CAPTCHA tokens.

#
ASI02: Tool Misuse and Exploitation
Medium
What this means

This can let automated workflows proceed through protections intended to distinguish humans from bots.

Why it was flagged

The browser automation workflow goes beyond solving a challenge and instructs how to place the resulting token into the page to bypass the site's CAPTCHA gate.

Skill content
Inject token - Set `g-recaptcha-response` or callback
Recommendation

Require clear user intent and authorization before using token injection, and avoid using it against third-party sites without permission.

#
ASI04: Agentic Supply Chain Vulnerabilities
Medium
What this means

The code installed later may differ from what the skill reviewer saw, and a compromised or changed upstream file would run as a local command.

Why it was flagged

The install path downloads executable code from a mutable GitHub branch and places it in a system-wide executable directory, while the reviewed artifact set contains no copy of that code or pin/hash.

Skill content
curl -fsSL https://raw.githubusercontent.com/adinvadim/2captcha-cli/main/solve-captcha \
  -o /usr/local/bin/solve-captcha && chmod +x /usr/local/bin/solve-captcha
Recommendation

Inspect the upstream script before installing, prefer a pinned release or commit hash, verify checksums, and avoid writing to system-wide paths unless necessary.

#
ASI03: Identity and Privilege Abuse
Low
What this means

Anyone with access to the key could use the user's 2Captcha account balance.

Why it was flagged

The skill uses a 2Captcha API key, which is expected for the service, but it is still a credential that can spend account balance if exposed or misused.

Skill content
echo "YOUR_API_KEY" > ~/.config/2captcha/api-key

# Or use environment variable
export TWOCAPTCHA_API_KEY="your-key"
Recommendation

Store the API key securely, restrict shell history exposure when setting it, and rotate it if it may have been exposed.

#
ASI07: Insecure Inter-Agent Communication
Low
What this means

Sensitive page context or images could be exposed to the 2Captcha provider or its human solvers if used carelessly.

Why it was flagged

The service is external and human-powered, so CAPTCHA images, site URLs, sitekeys, or text prompts used in commands may be sent outside the local environment.

Skill content
Solve CAPTCHAs programmatically using the 2Captcha human-powered service.
Recommendation

Do not submit CAPTCHAs or page URLs containing confidential information, and review 2Captcha's data handling terms before use.