skills/wazootech/wazoo-skills/wazoo/Gen Agent Trust Hub

wazoo

Pass

Audited by Gen Agent Trust Hub on Oct 24, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill handles authentication via environment variables (WAZOO_PLATFORM_TOKEN, WORLDS_TOKEN), avoiding the exposure of hardcoded secrets.
  • [SAFE]: All network operations are restricted to the vendor's official domains (api.wazoo.dev, data.wazoo.dev) for legitimate graph management operations.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external content through import and search functionalities, which could be exploited to inject instructions into the agent context. Ingestion points: Data import and search parameters in SKILL.md; Boundary markers: None present; Capability inventory: Network requests via curl to vendor domains; Sanitization: No sanitization or validation of the ingested content is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 24, 2026, 01:15 AM