my-sync-us-revenue
Warn
Audited by Gen Agent Trust Hub on Aug 11, 2026
Risk Level: MEDIUMPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes data from external financial APIs, creating a surface for Indirect Prompt Injection where malicious content in transaction descriptions could influence agent behavior.
- Ingestion points: Financial data is retrieved from Bill.com and Plaid API endpoints and processed by the
sync_us_revenue.pyscript. - Boundary markers: The instructions do not define delimiters or special handling to differentiate between data and instructions during processing.
- Capability inventory: The agent has the ability to perform network requests, modify Google Sheets, and send Slack notifications.
- Sanitization: No validation or sanitization of external content is mentioned in the documentation or script execution flow.
- [COMMAND_EXECUTION]: The skill utilizes a persistence mechanism to maintain recurring access and execution on the host system.
- Evidence: The documentation specifies the use of a macOS Launch Agent located at
~/Library/LaunchAgents/net.eoeoeo.sync-us-revenue.plistto automate the script execution every hour.
Audit Metadata