flowstudio-power-automate-monitoring
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from Power Automate, including flow names, descriptions, and maker information, which could contain malicious instructions intended to influence the agent.
- Ingestion points: Data is retrieved from external environments using tools such as list_store_flows, get_store_flow, list_store_makers, and list_store_power_apps.
- Boundary markers: The skill instructions do not define delimiters or provide specific instructions to the agent to ignore potentially malicious embedded content within the ingested flow metadata.
- Capability inventory: The skill possesses the capability to modify flow metadata through update_store_flow and can change flow execution states using set_live_flow_state.
- Sanitization: The documentation does not indicate that any sanitization or validation is performed on external content before it is processed by the agent.
Audit Metadata