surge

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly instructs using --remote password@host:port, which requires embedding a plaintext password in CLI arguments (verbatim secret handling), creating a high exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly exposes the agent to arbitrary network/third-party content via commands documented in references/command-reference.md such as "retrieve-data" (fetch captured request/response bodies), "watch request" and "dump request", which require the agent to read and act on untrusted request/response payloads as part of its workflow.