jina-reader

Warn

Audited by Snyk on Mar 6, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to use nodes to curl https://r.jina.ai/https://, which fetches and ingests arbitrary public webpages (user-provided URLs) for the agent to read and act on, exposing it to untrusted third-party content that could supply instructions.

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

  • Potentially malicious external URL detected (high risk: 0.90). The skill requires running curl at runtime to fetch and inject third‑party content from https://r.jina.ai/... (and the related https://s.jina.ai/...), which directly supplies text that will be injected into the agent's context and is a required runtime dependency.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 6, 2026, 04:20 PM