Skills
skills/thinkfleetai/thinkfleet-engine/azure-cosmosdb/Gen Agent Trust Hub

azure-cosmosdb

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes Azure CLI (az) and jq commands for infrastructure management.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes database query results. 1. Ingestion points: az cosmosdb sql container query output. 2. Boundary markers: None. 3. Capability inventory: Resource management and credential access via az cosmosdb. 4. Sanitization: None detected.
  • [SAFE]: No malicious patterns, such as obfuscation or exfiltration to third-party domains, were identified. The commands are appropriate for the tool's stated purpose and use well-known service tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 05:13 AM