digital-archive

Warn

Audited by Snyk on Feb 15, 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). The ArchiveWorkflow clearly scrapes and ingests open web and social-media content (see the architecture "Web Scraping / Social Media" and ArchiveWorkflow.process_url which calls self.scraper.fetch(url)) and then the pipeline reads that untrusted user-generated text with the AI categorizer and entity extractor, exposing the agent to indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 09:33 PM