scenario-model-training
Warn
Audited by Snyk on Oct 17, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).
- Direct money access detected (medium risk: 0.30). The skill describes training custom models and voice clones using the Scenario MCP API, which includes initiating training runs ("launching training", "spending the whole quote", and executing
trainactions likestart). These constitute direct financial operations (purchasing/charging for a training run). However, the documentation notes that the API requires authentication, team IDs, project IDs, and specific tool execution permissions (e.g., "Training tools are not in the default toolset: get schemas withscenario_tools_search, run reads... and writes... viascenario_tool_execute_write, or reconnect with?toolsets=full"). This represents service-level API credential access control rather than an unguarded direct payment path.
Issues (1)
W009
MEDIUMDirect money access capability detected (payment gateways, crypto, banking).
Audit Metadata