db-core/custom-adapter
Warn
Audited by Snyk on Mar 30, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's sync and loadSubset workflows explicitly fetch and subscribe to arbitrary endpoints (e.g., fetch(config.endpoint), myWebSocket.subscribe(config.endpoint), and fetch(
/api/items?...) in SKILL.md) and parse/process the returned JSON/events as part of its runtime, exposing the agent to untrusted third‑party content that can influence behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata