generate-sandbox-policy
Warn
Audited by Snyk on Nov 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow fetches outsider-authored web content, namely user-supplied API doc URLs and web-search results during auto-discovery for well-known services (SKILL.md lines 71, 136-139), but the agent must actively search or fetch these pages and no monitored inbox or feed is read.
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (low risk: 0.10). The skill can write or edit sandbox network policy files and attach middleware that govern a running sandbox's network enforcement (an operational change), but it documents no irreversible loss of operational state, so the scope gate cannot reach high.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata