importing-push-tokens
Pass
Audited by Gen Agent Trust Hub on Nov 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes device tokens and user identifiers exported from external platforms, which represents a surface for indirect prompt injection.
- Ingestion points: Data is sourced from external platform CSV exports or API responses (OneSignal, Braze, Customer.io, Airship, Firebase) as detailed in
references/exporting-devices.md. - Boundary markers: The instructions do not define specific prompt delimiters or instructions to ignore embedded commands within the processed data.
- Capability inventory: The skill uses the
integrations-push-tokens-createtool to import and store batches of data into the PostHog environment. - Sanitization: The instructions focus on validating the format and channel compatibility of tokens but do not include security-specific sanitization for potentially malicious content in user-controlled fields.
Audit Metadata