skills/alva-ai/skills/alva/Gen Agent Trust Hub

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/http module and various SDK modules (referenced in references/adk.md and references/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
Risk Level
SAFE
Analyzed
Mar 17, 2026, 03:18 AM