fetch4ai

Warn

Audited by Snyk on Mar 10, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and processes arbitrary public web pages (via the --url parameter shown in SKILL.md and scripts/fetch4ai.py) and returns LLM-ready markdown that web-research subagents are instructed to read and synthesize, meaning untrusted third-party page content can directly influence agent actions.

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

  • Potentially malicious external URL detected (high risk: 0.90). The skill fetches arbitrary external pages at runtime (e.g., https://example.com) and returns their cleaned markdown for use in agent/web-research prompts, meaning remote page content can directly control model input and thus agent instructions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 01:47 AM