2captcha
3 findings (1 critical, 2 high), mainly command injection, data exfiltration, social engineering. Most recent scan 2026-02-05.
This skill presents CRITICAL security risks and ethical concerns. The primary threat is arbitrary remote code execution through unverified script downloads from GitHub, which could allow complete system compromise. Additionally, the skill instructs users to store API credentials in plaintext files, creating credential theft risks. Most concerning is the skill's explicit purpose: bypassing CAPTCHA security controls designed to prevent automated abuse. While CAPTCHA-solving services have legitimate uses (accessibility, authorized testing), this skill provides no ethical guidelines, legal warnings, or use restrictions. The combination of insecure installation practices, poor credential management, and facilitation of security control circumvention makes this skill unsuitable for distribution without major security and ethical improvements. The missing metadata (license, compatibility, allowed-tools) and broken reference (page.py) further indicate insufficient quality control.
Scanner's overall assessment (LLM analyzer)
Second scanner: NVIDIA SkillSpector
Independent static run, no language model, over the same files as the Cisco scan above. How the two scanners compare across the whole corpus: Two scanners, one corpus.
What this skill does
Solve CAPTCHAs using 2Captcha service via CLI. Use for bypassing captchas during web automation, account creation, or form submission.
- Package
- 2 files, 7.2 KB
- SKILL.md
- 406 words, 12+ sections
- Code
- None. Instructions only.
SKILL.md covers: 2Captcha Skill · Installation · One-line install · Verify · Configuration · Save your 2Captcha API key · Or use environment variable · Quick Reference · Check Balance First · Image CAPTCHA · From file · From URL
Findings
CRITICAL Arbitrary Remote Code Execution via Unverified Script Download Command Injectionllm
The installation instructions direct users to download and execute a bash script from GitHub without any integrity verification (no checksum, signature, or hash validation). The script is immediately made executable and placed in a system directory (/usr/local/bin/). An attacker who compromises the GitHub repository or performs a man-in-the-middle attack could inject malicious code that would be executed with the user's privileges. This represents arbitrary code execution with no security controls.
SKILL.md
curl -fsSL https://raw.githubusercontent.com/adinvadim/2captcha-cli/main/solve-captcha \
-o /usr/local/bin/solve-captcha && chmod +x /usr/local/bin/solve-captchaHIGH Hardcoded API Key Storage in Plaintext Configuration File Data Exfiltrationllm
The skill instructs users to store their 2Captcha API key in plaintext in ~/.config/2captcha/api-key without any encryption or access controls. API keys are sensitive credentials that provide access to paid services and should be protected. Storing them in plaintext makes them vulnerable to theft by malware, other users on shared systems, or accidental exposure through backups/logs. The skill also suggests using environment variables, but the primary instruction is plaintext file storage.
SKILL.md
mkdir -p ~/.config/2captcha
echo "YOUR_API_KEY" > ~/.config/2captcha/api-keyHIGH Facilitation of CAPTCHA Bypass for Potentially Malicious Automation Social Engineeringllm
The skill's stated purpose is to 'bypass captchas during web automation, account creation, or form submission.' CAPTCHAs exist as security controls to prevent automated abuse, bot attacks, spam, and fraudulent account creation. This skill explicitly facilitates circumventing these security measures. While there may be legitimate accessibility or testing use cases, the skill provides no ethical guidelines, warnings about terms of service violations, or restrictions on use. The workflow section specifically describes browser automation to inject CAPTCHA tokens, which is commonly used for malicious purposes including credential stuffing, spam, scraping protected content, and mass account creation for fraud.
SKILL.md
Description: Solve CAPTCHAs using 2Captcha service via CLI. Use for bypassing captchas during web automation, account creation, or form submission.
Workflow for Browser Automation section describes injecting tokens to bypass security controls.What is in the package
| File | Kind | Size |
|---|---|---|
README.md | doc | 3.9 KB |
SKILL.md | doc | 3.3 KB |
External hosts referenced
2captcha.com github.com raw.githubusercontent.com site.com
Hostnames that appear in the skill's files. Referencing a host is not a finding; compare against the findings above and the skill's stated purpose.
Environment variables referenced
ERROR_WRONG_CAPTCHA_ID TWOCAPTCHA_API_KEY
Package contents recorded 2026-10-22. The scan above ran against the version current at scan time; the two can differ if the skill has since been updated.
What we checked
- Static analyzer. Pattern rules over SKILL.md and bundled files: known-bad commands, exfiltration URLs, secrets, obfuscation.
- Behavioral analyzer. Checks what the skill asks the agent to do against what its description claims it does.
- Llm analyzer. A language model reads the skill and reports intent-level issues the rules cannot express.
- Trigger analyzer. Looks for instructions that fire on conditions the user did not ask for.
- Meta analyzer. A second model pass that validates, deduplicates and re-scores the other analyzers' findings.
What we did not check
- Runtime behaviour. The skill was not executed; findings come from reading its files.
- Anything fetched at install or run time, including remote scripts, package dependencies, and URLs the skill tells the agent to open.
- Content the analyzers cannot read: images, binaries, and some non-English text.
- Known scanner bypass classes. See the methodology and limitations page.
Sources
- Repository: https://clawhub.ai/skills/2captcha
- Raw scan result: 2captcha-cli-scan.json
- Badge for your README:
- Request a re-scan