share-reading

Warn

Audited by Snyk on Mar 7, 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's Step 1 explicitly requires using WebFetch to retrieve and extract title/author/key points from user-provided URLs (web pages), meaning the agent ingests untrusted public third-party content and uses it to drive post-generation.

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

  • Potentially malicious external URL detected (high risk: 0.90). The skill explicitly fetches user-provided web pages at runtime via WebFetch and injects that fetched content into the model prompt (e.g., https://example.com/article-about-rust-in-linux), so external URLs can directly control the agent's outputs.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 7, 2026, 02:32 PM