design-harness-agent-skill

Warn

Audited by Snyk on Jul 30, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (medium risk: 0.30). In the “Filing Sources” workflow, when the user “drops URLs/PDFs” the agent reads the source material and extracts key claims to create markdown cards in sources/, meaning outsider-authored text supplied via URLs/PDFs is ingested at runtime.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 30, 2026, 12:59 AM
Issues
1
Security Audit — snyk — design-harness-agent-skill