fetching-blocked-urls

Warn

Audited by Snyk on Feb 16, 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 calls Jina's reader (https://r.jina.ai/TARGET_URL) to fetch and return markdown from arbitrary public URLs, which the agent ingests and interprets—exposing it to untrusted third-party web content that could contain indirect prompt injections.

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

  • Potentially malicious external URL detected (high risk: 0.90). The skill explicitly issues runtime fetches to https://r.jina.ai/TARGET_URL (via curl) to retrieve arbitrary markdown pages that are then returned/injected as the agent's content/fallback context, so remote content can directly control prompts or include executable instructions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:00 PM