skills/bytedance/agentkit-samples/byted-sol-stability-grafana-dashboard-assembly/Gen Agent Trust Hub
byted-sol-stability-grafana-dashboard-assembly
Pass
Audited by Gen Agent Trust Hub on Jul 14, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXFILTRATION]: The skill connects to Prometheus and Grafana endpoints to validate metrics and dashboard connectivity. It handles authentication credentials provided at runtime via command-line arguments. This behavior is consistent with the skill's primary function and follows standard practices for monitoring tools.- [PROMPT_INJECTION]: The skill processes multiple JSON configuration files, which is a potential surface for indirect prompt injection. However, the transformation logic is contained within Python modules, and the agent's role is governed by instructions that focus on validation reporting.
- Ingestion points: Input files like --sli-spec and --metrics-catalog are read and parsed in src/grafana_dashboard_assembly_skill/input_normalizer.py.
- Boundary markers: There are no specific boundary markers used to delineate user data from system instructions in the input JSON files.
- Capability inventory: The skill has the ability to perform network requests (urllib.request) and write files to the output directory (src/grafana_dashboard_assembly_skill/exporter.py).
- Sanitization: The skill relies on JSON structure for data isolation, though it doesn't implement advanced content sanitization for the strings passed into the dashboard structure.
Audit Metadata