downloading-batch-export-files
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill facilitates official data export functionality for the PostHog platform.
- [DATA_EXPOSURE]: While the skill involves downloading potentially sensitive data (events, person records), it includes security best practices such as using the existing platform authentication context and explicitly warns against sharing temporary signed URLs with third-party services.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the platform (HogQL results and event data). However, it mitigates risk by instructing the agent to treat outputs as file downloads and avoid displaying large or binary content in the chat interface, which prevents the agent from interpreting data content as instructions.
- [COMMAND_EXECUTION]: The skill uses parameterized tool calls and REST API requests which are standard for the platform and do not involve arbitrary shell command execution.
Audit Metadata