troubleshoot-docker
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill acts as an instructional guide for diagnosing Docker issues using Netdata. It utilizes specific, restricted tools for querying metrics and does not exhibit malicious patterns such as remote code execution, credential harvesting, or unauthorized data exfiltration.
- [PROMPT_INJECTION]: Analysis of the instructions reveals no attempts to bypass safety filters or override agent behavior.
- [PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection by ingesting external telemetry data (metrics and alerts) from Netdata. Evidence: 1. Ingestion points: MCP tools
query_metrics,list_metrics, andfind_anomalous_metrics(SKILL.md). 2. Boundary markers: Not explicitly implemented. 3. Capability inventory: Restricted to read-only diagnostic queries; no subprocess or arbitrary file access detected. 4. Sanitization: None observed. The risk is considered minimal as the skill does not possess the capabilities required to exploit the data ingestion surface.
Audit Metadata