engagement-suppression-workflow

Warn

Audited by Snyk on Apr 9, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs using the "Claude Anthropic Chrome extension" so Claude can "see and interact with the HubSpot workflow builder UI" (a third‑party web UI containing user-generated contact data), which the agent would read and act on as part of its workflow, creating a clear avenue for untrusted content to influence actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 9, 2026, 04:20 AM
Issues
1