konnect-event-gateway
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security concerns were identified during the analysis.
- [PROMPT_INJECTION]: The skill instructions are focused on troubleshooting logic and do not contain attempts to bypass agent constraints or safety filters.
- [DATA_EXFILTRATION]: No evidence of sensitive file access (e.g., credentials, SSH keys) or network exfiltration to unauthorized domains.
- [REMOTE_CODE_EXECUTION]: The skill does not perform remote script downloads or execute untrusted code. It uses established tools like
kongctlandterraformfor their intended diagnostic and declarative purposes. - [COMMAND_EXECUTION]: Shell commands referenced (
kongctl-query,kongctl-declarative) are specific to the Kong Konnect platform and are used appropriately within the troubleshooting workflow. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from live gateway inspection and user-provided artifacts. While it lacks explicit boundary markers, its primary function is read-only diagnostic analysis (
kongctl-query), minimizing the risk of unauthorized state changes.
Audit Metadata