generating-flow

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The skill explicitly requires sending grounded org schema and local sfdx project metadata to a named external MCP tool and mandates repeated, unattended calls (no user confirmation), which creates a clear vector for data exfiltration and remote-control style abuse.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The workflow ingests outsider-authored free text via the userPrompt input to the required MCP calls fetchGroundedObjectMetadata → flowElementSelection for every user request.