greptimedb-trigger
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- [PROMPT_INJECTION] (SAFE): No attempts to override system instructions or bypass safety filters were found in the skill content.
- [DATA_EXFILTRATION] (SAFE): No patterns of unauthorized data exfiltration or access to sensitive local files were detected. Standard examples for Alertmanager (localhost:9093) are used correctly as placeholders.
- [EXTERNAL_DOWNLOADS] (SAFE): The skill references documentation URLs for information retrieval using WebFetch but does not download or execute external code, scripts, or packages.
- [INDIRECT_PROMPT_INJECTION] (LOW): The skill possesses an ingestion surface by reading external documentation (Phase 1) and user-provided rules (Phase 2). This is assessed as LOW risk because the skill only generates SQL text for display and lacks the capability to execute commands or modify the file system.
Audit Metadata