data-explorer

Fail

Audited by Snyk on Nov 13, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (medium risk: 0.30). The skill is a data-to-dashboard template whose behavior serves the user, but page.html runs whatever script the page holds and, when the slots are empty, fetches and executes app.js from a remote Drop URL on every open, which is unpinned remote code execution that the user would not expect.

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

  • Third-party content exposure detected (low risk: 0.10). The required workflow reads a user-supplied dataset (CSV, JSON export or API) and prints sample rows during profiling (step 2), so free-text fields in that data could carry outsider-authored content, but the user chooses the source and the agent does not search for or fetch outsider content itself.

Issues (2)

E004
CRITICAL

Prompt injection detected in skill instructions.

W011
MEDIUM

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

Audit Metadata
Risk Level
CRITICAL
Analyzed
Nov 13, 2026, 04:35 PM
Issues
2