Skill audit report

ai-calls-china-phone Audit report.

AI 外呼、机器人外呼、智能外呼与 AI 电话 Skill。当用户说“帮我打电话”“打电话给商家”“预约电话”,或需要电话机器人完成通知、预约、咨询和经授权的客户回访时使用。支持直接拨打国内手机号、中文通话、逐次确认、AI 呼入接待、智能体、实时转写、通话记录、余额和费用查询。

BLOCKED · BLOCKNeeds reviewGenerated Oct 17, 2026Heuristic metadata audit
67
Audit
58
Trust
55
Quality
70
Security
88
Maintain
92
Install

OpenAgentSkill Trust Score

58
Manual review

OpenAgentSkill Trust Score

The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.

GitHub adoption

FAIL

30

12 GitHub stars

Stars/forks activity

FAIL

32

12 stars, 2 forks; issue activity unavailable in current metadata

Recent maintenance

PASS

88

2mo since push

License clarity

PASS

86

MIT-0

README/SKILL.md completeness

PASS

86

Metadata includes enough usage and workflow context

Dependency/runtime risk

WARN

46

command execution surface, credential or environment access

Install availability

PASS

92

npx skills add ustczz/openclaw-ai-calls-china-phone --skill ai-calls-china-phone

Install command safety

PASS

92

standard package or runtime install path

Permission surface

FAIL

36

secrets or environment access, shell or command execution

Repository evidence

PASS

86

https://github.com/ustczz/openclaw-ai-calls-china-phone/tree/main/skill

Review status

INFO

66

AI review data available

Agent Proven outcomes

INFO

54

No agent outcome data yet

Checks

Install and adoption review

6 Passed · 17 Needs review

Install path

92

PASS

npx skills add ustczz/openclaw-ai-calls-china-phone --skill ai-calls-china-phone

Repository

88

PASS

https://github.com/ustczz/openclaw-ai-calls-china-phone/tree/main/skill

License

86

PASS

MIT-0

Maintenance

88

PASS

2mo since push

AI review

55

CHECK

The skill makes real phone calls and sends phone numbers, conversation content, and transcriptions to a third-party API (Stepone AI). While the skill includes strong safety rules and requires explicit user confirmation, this inherently raises privacy and cost concerns that should be clearly communicated to end users.

README/SKILL.md completeness

86

PASS

Usable description available

Dependency risk

46

FIX

command execution surface, credential or environment access

Install command safety

92

PASS

standard package or runtime install path

Permission surface

36

FIX

secrets or environment access, shell or command execution

Stars/forks activity

32

FIX

12 stars, 2 forks; issue activity unavailable in current metadata

Adoption

42

CHECK

12 GitHub stars

Warnings

  • Dependency or permission surface needs review
  • Permission surface may require sandboxing
  • The skill makes real phone calls and sends phone numbers, conversation content, and transcriptions to a third-party API (Stepone AI). While the skill includes strong safety rules and requires explicit user confirmation, this inherently raises privacy and cost concerns that should be clearly communicated to end users.
  • The SKILL.md is entirely in Chinese. While this matches the target audience (China phone calls), it may hinder non-Chinese-speaking reviewers and users. Consider adding an English summary or bilingual sections.
  • The client script (stepone_client.py) is only partially included in the excerpt. Full code review is limited, but the visible portions show proper input validation and environment-based configuration.
  • The skill depends on an external API that is not open-source and may change its service terms. The repository does not include an explicit disclaimer about this dependency.
  • Low GitHub adoption signal
  • Quality score needs review
  • Permission surface needs review: secrets or environment access, shell or command execution
  • GitHub adoption: 12 GitHub stars
  • Stars/forks activity: 12 stars, 2 forks; issue activity unavailable in current metadata
  • Dependency/runtime risk: command execution surface, credential or environment access

Method

This report combines public metadata, AI review output, repository freshness, install readiness, OpenAgentSkill events, quality scoring, trust checks, and the agent safety gate. It is not a full source-code security review.

Compare nearby options

Related skills to audit next