downloading-batch-export-files
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes raw PostHog data (events, persons, or sessions) which may contain attacker-controlled strings from external sources.
- Ingestion points: Data is ingested into the agent context from the PostHog REST API at
/api/projects/{project_id}/file_download_batch_exports/{run_id}/download/. - Boundary markers: The instructions do not define delimiters or specific markers to distinguish the raw data from potential instructions.
- Capability inventory: The skill has capabilities to perform authenticated network requests and write files to the local system.
- Sanitization: The content of the exported files (Parquet or JSONLines) is saved without sanitization or validation of the internal data fields.
- [DATA_EXFILTRATION]: The skill performs network operations to download sensitive data and handles temporary signed access URLs.
- The skill makes authenticated HTTP GET requests to PostHog's API infrastructure to fetch data exports.
- The skill documentation correctly identifies a data exposure risk, noting that signed URLs grant temporary access to exported files and should not be shared with unrelated services.
Audit Metadata