use-ravion

Fail

Audited by Snyk on Nov 17, 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 legitimate Ravion deployment guide, but it has the agent install an MCP server via npx that writes into the agent host's config without asking, and it pushes the agent to file friction reports to the vendor proactively, which the user may not expect.

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

  • Third-party content exposure detected (medium risk: 0.30). Application logs from the user's own deployed web services, read through ravion module logs during debugging, can contain text that outside visitors control (for example request paths, headers, or form input echoed by the app), so the required debug workflow ingests outsider-influenced text without a specific item being selected.

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 17, 2026, 05:08 PM
Issues
2