mssql-operations-debugging
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists exclusively of markdown documentation and reference guides. It does not include any executable scripts, binaries, or configuration that would automate dangerous operations.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a process for analyzing external telemetry that could theoretically contain malicious instructions.
- Ingestion points: Application logs, traces, and Query Store telemetry (referenced in SKILL.md and references/01-evidence-and-query-diagnostics.md).
- Boundary markers: Not specified for log ingestion.
- Capability inventory: The skill itself has no operational capabilities and does not perform subprocess execution, network requests, or file system modifications.
- Sanitization: Not mentioned, although the skill includes a 'Security Signals' section to detect injection. As this is a procedural guide for diagnostics, the surface does not pose a direct threat to the agent environment.
- [SECURITY_BEST_PRACTICES]: The documentation actively promotes security during the debugging process, instructing users to check for SQL injection attempts, overprivileged accounts, and exposed connection strings or secrets in logs and traces.
Audit Metadata