revops-crisis
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill outlines workflows where the agent ingests and analyzes external business data (e.g., deal notes, win-loss reasons, and CRM fields), which serves as an entry point for indirect prompt injection. \n
- Ingestion points: Data is ingested from external CRM systems (Salesforce, HubSpot) and data warehouses (Supabase). \n
- Boundary markers: The instructions do not define specific delimiters or isolation techniques to separate external data from the system instructions. \n
- Capability inventory: The skill includes instructions for the agent to trigger Slack alerts and CRM workflow updates based on the results of the data analysis. \n
- Sanitization: No specific filtering or validation steps for external business data are mentioned before it is processed by the agent.
Audit Metadata