hr-monthly-selfcheck-free

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (critical risk: 1.00). The skill contains instructions and code designed to facilitate payment interactions and purchases through external mechanisms (SkillPay), which constitutes monetization solicitation within a non-financial skill.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill contains instructions and code snippets directing the agent to download and execute an external installer package (@alipay/agent-payment) from an unverified public registry source via npx during setup/runtime, constituting a weak/unknown operational dependency.