parallel-web-extract

Warn

Audited by Snyk on Feb 23, 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). This skill's SKILL.md "Extract Request" curl example and usage notes show it fetches and scrapes arbitrary public URLs via Parallel AI (the "url" field), so the agent ingests untrusted third-party webpage content that can influence its outputs and follow-up actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 23, 2026, 12:01 PM