scbe-mobile-connector-orchestrator
Pass
Audited by Gen Agent Trust Hub on Jun 24, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its architecture of ingesting and acting upon data from external connectors.
- Ingestion points: Data from external services (Shopify, Zapier, Discord, etc.) is ingested during the goal advancement process (
POST /mobile/goals/{goal_id}/advance). - Boundary markers: The skill lacks explicit delimiters or instructions to treat data from connectors as untrusted or to ignore any natural language instructions embedded within the payloads.
- Capability inventory: The skill possesses the capability to execute network requests via PowerShell's
Invoke-RestMethodand manages autonomous goal-oriented workflows. - Sanitization: There is no evidence of sanitization or validation logic for the content returned by external connectors before it influences the agent's context and next steps.
Audit Metadata