NYC

galaxy-automation

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 prompt includes examples and explicit guidance that embed API keys directly into command-line strings (e.g., --galaxy_user_key) and even states "use full key in command," which requires the LLM to handle/output secret values verbatim.

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

  • Third-party content exposure detected (high risk: 0.80). This skill connects to public Galaxy instances (e.g., https://usegalaxy.org) and uses BioBlend/Planemo to fetch and parse histories, datasets, job stderr, and invocation details — all of which can be user-generated/untrusted content that the agent reads and interprets.
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 15, 2026, 09:42 PM