NYC

vm0-agent

Fail

Audited by Snyk on Feb 18, 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 instructs the agent to ask users to paste API tokens and includes examples that embed secret values verbatim into CLI commands (e.g., vm0 secret set ... --body "secret_xxx"), which requires the LLM to handle/output secrets directly.

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

  • Third-party content exposure detected (high risk: 0.90). The skill's create/innovate workflows explicitly instruct fetching and processing public, user-generated content (e.g., HackerNews, RSS feeds, YouTube, CoinGecko, competitor websites and crawling via skills like firecrawl, and searching skills.sh with curl to https://skills.sh/api/search?q=), which the agent is expected to read and interpret.
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 18, 2026, 04:49 PM