upwork-proposal

Warn

Audited by Snyk on Mar 1, 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). This skill requires the user to paste an Upwork job description (see SKILL.md "Required Input: job_description") and explicitly instructs the agent to read and follow hidden/test instructions from the posting, so it ingests untrusted, user-generated third-party content (public Upwork job posts) that can directly influence actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 12:36 AM