infrastructure-engineer

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches company synchronization data from the vendor-owned domain https://wazoo.dev.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting external JSON-LD data to synchronize context.
  • Ingestion points: External fetch of https://wazoo.dev defined in SKILL.md.
  • Boundary markers: No delimiters or ignore instructions are provided for the ingested data.
  • Capability inventory: CI/CD pipeline management, IaC automation, and access control as described in SKILL.md.
  • Sanitization: No explicit validation or sanitization logic is present for the remote graph data.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 11:53 PM