upwork-apply

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 explicitly scrapes public, user-generated Upwork job listings via scripts/upwork_apify_scraper.py (Apify API) and then injects job titles/descriptions/skills into prompts in scripts/upwork_proposal_generator.py to generate proposals with Anthropic, so untrusted third-party content directly influences model behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 6, 2026, 02:19 PM