flowstudio-power-automate-monitoring

Pass

Audited by Gen Agent Trust Hub on Apr 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: Credential Security: The skill requires the FLOWSTUDIO_MCP_TOKEN environment variable for authentication, which is a secure practice that avoids hardcoding secrets.- [PROMPT_INJECTION]: Indirect Ingestion Point: The skill retrieves and processes data from external sources, including flow descriptions and maker inputs. While this represents a surface where an attacker with control over the Power Automate environment could attempt to inject instructions, it is an expected part of the monitoring process.- [DATA_EXFILTRATION]: Functional Data Access: The skill allows for the retrieval of flow definitions, connection details, and environment configurations. This behavior is documented and essential for its monitoring and governance capabilities and does not constitute unauthorized data exfiltration.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 9, 2026, 01:03 AM