svix-new-integration
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill conducts discovery interviews and generates implementation plans for Svix integrations. Its behavior is consistent with its stated purpose and administrative scope.
- [EXTERNAL_DOWNLOADS]: The skill references official documentation and resources from the vendor's domains (
docs.svix.com) and GitHub repositories (github.com/svix/*). These are well-known, trusted sources used to provide users with version-sensitive integration guidance. - [PROMPT_INJECTION]: There are no indicators of attempts to override agent behavior, bypass safety guidelines, or extract system prompts. The instructions focus on structured questioning and quoting user input accurately.
- [DATA_EXFILTRATION]: No patterns of unauthorized data collection or exfiltration were detected. The skill specifically instructs users to store sensitive credentials like
SVIX_AUTH_TOKENand webhook secrets (whsec_...) in secure environment variables or secret managers, explicitly stating they should never be exposed to frontend bundles. - [COMMAND_EXECUTION]: The skill suggests standard package installation commands (e.g.,
npm install svix,pip install svix) for the user to include in their implementation plan. It does not attempt to execute these commands automatically or use dangerous shell execution patterns.
Audit Metadata