activitykit
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill documents the handling of external push notification payloads that update the agent's display state.
- Ingestion points:
aps.content-stateJSON payloads received via APNs, as described inreferences/lifecycle-updates-and-push.md. - Boundary markers: Strict enforcement of Swift
Codableprotocols ensures incoming data matches the pre-definedContentStateschema. - Capability inventory: The skill is limited to updating visual elements on the Lock Screen and Dynamic Island; it does not possess capabilities for file modification, arbitrary command execution, or sensitive data access.
- Sanitization: The documentation explicitly advises developers not to include secrets in attributes or state and relies on the framework's internal sandboxing for display.
- [EXTERNAL_DOWNLOADS]: The skill contains references to external documentation and testing tools.
- Provides links to a documentation viewer at
sosumi.ai. - Includes a
curlexample for testing push updates against Apple's official APNs gateway (api.push.apple.com).
Audit Metadata