reply-mcp

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill's examples explicitly show embedding a personal API key into a command/header (and exporting it on the shell), which requires the agent to handle or emit secret values verbatim and therefore poses an exfiltration risk.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly configures and uses the runtime connector URL https://mcp.reply.io to fetch and invoke the remote "reply_*" tool catalog (remote tool executions), meaning that external code/services at that URL control agent-executed actions.