alva
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill serves as a technical reference for a legitimate financial platform. Its features, such as cloud-side JavaScript execution and cloud filesystem access, are performed within a secure, sandboxed V8 runtime on the Alva servers, preventing any unauthorized access to the user's local machine or environment.
- [PROMPT_INJECTION]: The skill possesses a surface area for indirect prompt injection (Category 8).
- Ingestion points: Financial data is fetched from external sources via the
net/httpmodule and various SDK modules (referenced inreferences/adk.mdandreferences/feed-sdk.md). - Boundary markers: The documentation does not explicitly mandate the use of delimiters or 'ignore' instructions when processing external data through the agent loop.
- Capability inventory: The platform environment supports filesystem operations (
alfs), network requests (net/http), and automated scheduling (cronjobs). - Sanitization: There are no documented requirements for sanitizing or validating external content before it is interpolated into agent prompts.
Audit Metadata