captcha-solver

Fail

Audited by Snyk on Feb 13, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 1.00). The skill's setup example instructs storing the 2Captcha API key by passing the secret directly on the command line (--value <your_key>), which requires handling/outputting the secret verbatim and is an insecure pattern.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). The skill uses the browser_subagent to interact with arbitrary web pages (detecting "I'm not a robot" challenges) and may ingest/read page content or screenshots from untrusted public sites (and optionally send them to the 2Captcha third‑party API), so it consumes untrusted third‑party content as part of its workflow.
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 13, 2026, 02:54 PM