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 Bash tool 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, and support platforms as described in references/data-and-calculations.md.
  • Boundary markers: The references/output-template.md does 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, and WebSearch tools.
  • 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.yaml file to calculate growth rates and other KPIs at runtime.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 07:26 AM
Security Audit — agent-trust-hub — weekly-business-report