nebula-ai
Warn
Audited by Snyk on Oct 9, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The workflow interacts with external services (Gmail, Slack, GitHub, Linear) and ingests messages, files, issues, and web content returned by Nebula agents, which can contain outsider-authored free text via monitored feeds and delegated threads.
MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).
- Direct money access detected (high risk: 0.70). The skill delegates tasks to AI agents via the
nebula-aiCLI, which can perform general writes including "purchasing" (SKILL.md:63). Although purchasing is listed among potential write operations, the skill itself provides instructions for delegation and management rather than implementing a direct financial transaction route with dedicated independent access controls in the prompt. Since it supports direct operations (purchasing) without a documented qualifying independent financial control in the skill definition, it falls under high severity.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W009
MEDIUMDirect money access capability detected (payment gateways, crypto, banking).
Audit Metadata