agent-sandbox

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill's example mcp__flow-nexus__sandbox_create call includes env_vars with API_KEY as a literal value, which encourages the agent to accept and embed secret values verbatim in generated calls/outputs.

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

• Third-party content exposure detected (low risk: 0.10). The required workflow only uses first-party, skill-defined MCP calls (e.g., mcp__flow-nexus__sandbox_create/execute/upload) with user-provided code/file content directly passed to the sandbox, but there is no runtime path described that ingests outsider-authored free text from any external feed/queue/host before selecting a specific item.