Skill audit report
product-faq Audit report.
产品知识问答技能。当用户咨询产品参数、价格、库存、保修、退换货政策、售后渠道、物流、以旧换新、积分等产品相关信息时使用。
OpenAgentSkill Trust Score
OpenAgentSkill Trust Score
The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.
GitHub adoption
FAIL30
21 GitHub stars
Stars/forks activity
FAIL32
21 stars, 6 forks; issue activity unavailable in current metadata
Recent maintenance
PASS88
2mo since push
License clarity
PASS86
MIT
README/SKILL.md completeness
WARN60
Public metadata needs stronger README/SKILL.md context
Dependency/runtime risk
PASS90
no major dependency risk hints in public metadata
Install availability
PASS92
npx skills add zj-unicom-ai/UniEmployee --skill product-faq
Install command safety
PASS92
standard package or runtime install path
Permission surface
PASS100
no high-risk permission surface in public metadata
Repository evidence
PASS86
https://github.com/zj-unicom-ai/UniEmployee/tree/main/backend/skills/product-faq
Review status
INFO66
AI review data available
Agent Proven outcomes
INFO54
No agent outcome data yet
Checks
Install and adoption review
Install path
92
npx skills add zj-unicom-ai/UniEmployee --skill product-faq
Repository
88
https://github.com/zj-unicom-ai/UniEmployee/tree/main/backend/skills/product-faq
License
86
MIT
Maintenance
88
2mo since push
AI review
55
The skill invokes kb_search, CRM order_query, and start_refund tools without defining their interfaces, required permissions, or setup, so it is not fully portable outside the original agent environment.
README/SKILL.md completeness
84
Usable description available
Dependency risk
90
no major dependency risk hints in public metadata
Install command safety
92
standard package or runtime install path
Permission surface
100
no high-risk permission surface in public metadata
Stars/forks activity
32
21 stars, 6 forks; issue activity unavailable in current metadata
Adoption
42
21 GitHub stars
Warnings
- The skill invokes kb_search, CRM order_query, and start_refund tools without defining their interfaces, required permissions, or setup, so it is not fully portable outside the original agent environment.
- It lacks an explicit prompt-injection guardrail for knowledge-base retrieval results; the model should be told to treat retrieved text as data and ignore any instructions embedded in it.
- It does not specify how to handle conflicting search results or how to combine multiple source citations such as 'FAQ-001' and 'FAQ-002' into one answer.
- The scope includes inventory, but the workflow only mentions kb_search; it should clarify whether inventory is static knowledge-base content or requires a live lookup to avoid stale answers.
- Low GitHub adoption signal
- Quality score needs review
- GitHub adoption: 21 GitHub stars
- Stars/forks activity: 21 stars, 6 forks; issue activity unavailable in current metadata
- README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context
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