AGENT LAB: SKILLS

vibe-check

Fail

Audited by Snyk on Feb 15, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 1.00). The CLI examples explicitly show typing passwords/secret strings via commands (e.g., vibium type ... "secret"), which requires embedding secret values verbatim in generated commands/outputs and thus exposes them.

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

  • Third-party content exposure detected (high risk: 1.00). The skill exposes the agent to arbitrary public webpages via commands like "vibium navigate " and then reads that untrusted content with "vibium text", "vibium html", and "vibium eval", which can allow indirect prompt injection from third‑party sites.
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 15, 2026, 08:32 PM