openerp-domains
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXFILTRATION]: Facilitates access to broad organizational data including employee records (BD_Empinfo), customer/supplier details, and financial transactions. This is consistent with the skill's stated purpose of querying OpenERP domains and does not involve sending data to unauthorized external destinations.
- [COMMAND_EXECUTION]: Instructs the agent to execute the 'openerp' binary with various arguments. This binary is explicitly declared as a requirement in the skill metadata for legitimate business data retrieval.
- [PROMPT_INJECTION]: The skill processes data returned from an external ERP system, creating a surface for indirect prompt injection.
- Ingestion points: Data enters the agent context via the 'list' and 'view' subcommands of the 'openerp' tool (SKILL.md).
- Boundary markers: Absent; the skill does not instruct the agent to use specific delimiters or ignore instructions within the ERP data.
- Capability inventory: The agent can execute the 'openerp' CLI tool and format its output.
- Sanitization: No explicit sanitization or filtering of the ERP-returned content is mentioned.
Audit Metadata