baoyu-wechat-summary

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly requires copying verbatim message quotes from raw chat into the generated digest (and performs grep-based attribution checks), which forces the agent to output any secret values that may appear in chat messages verbatim.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.90). Flagged because the skill explicitly requires running every wx command with dangerouslyDisableSandbox: true (bypassing the runtime sandbox) and also advises using sudo for wx reinit, which encourages disabling security boundaries and elevating privileges.