automating-with-maia

Fail

Audited by Snyk on Mar 1, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 1.00). The prompt instructs users to paste webhook URLs and full HTTP request/auth details and tells the agent to hardcode/embed those URLs/headers into generated code, which forces the model to include secret values verbatim.

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

  • Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs Maia to perform website browsing and web scraping of public URLs (see "Maia Capabilities → Website browsing" and Example 2 "browse each competitor URL" in SKILL.md), meaning untrusted third‑party page content will be fetched and interpreted and can influence workflow decisions and outputs.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 1.00). The skill requires calling the Maia webhook URL https://hooks.modularmind.app/hooks/ at runtime to trigger deployed workflows (i.e., execute remote agent code/workflows), so this external URL is a required runtime dependency that executes remote code.
Audit Metadata
Risk Level
HIGH
Analyzed
Mar 1, 2026, 04:28 PM