openserv-multi-agent-workflows

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

• Third-party content exposure detected (high risk: 0.85). Outsider free text can enter the agent LLM context via runtime webhook trigger inputs (user-provided input/topic fields like {{trigger.topic}} / {{trigger.youtube_url}}) that get passed into downstream tasks, enabling indirect prompt injection from an external caller.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

• Direct money access detected (high risk: 1.00). This SKILL.md primarily documents multi-agent workflows, but it explicitly references a related skill that performs a crypto financial operation: "openserv-launch
• Launch tokens on Base blockchain" (line 177). That is a specific blockchain/token launch capability (crypto execution), which qualifies as Direct Financial Execution.