weekly-business-report
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
Bashtool to execute database queries and process data snapshots from various sources. - [INDIRECT_PROMPT_INJECTION]: The skill aggregates data from external sources such as CRM records, email metrics, and support tickets, which may contain adversarial instructions.
- Ingestion points: Data is ingested from
Supabase,CRM,email, andsupportplatforms as described inreferences/data-and-calculations.md. - Boundary markers: The
references/output-template.mddoes not specify the use of delimiters or instructions to prevent the agent from interpreting ingested data as commands. - Capability inventory: The skill is granted access to the
Bash,Write, andWebSearchtools. - Sanitization: There are no documented procedures for sanitizing or validating external data before it is included in the reporting workflow.
- [DYNAMIC_EXECUTION]: The skill evaluates mathematical formulas defined in the
config.yamlfile to calculate growth rates and other KPIs at runtime.
Audit Metadata