specification-architect
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill's Phase 0 "Initial Search" and "Mandatory Verification" explicitly require using WebSearch and WebFetch to browse and read third-party URLs from the open web, meaning the agent will ingest and interpret untrusted public content as part of its workflow.
Audit Metadata