aftership-ai-layer Audit report.

Warnings

• SKILL.md describes AfterShip as a '全球ERP、库存、订单与履约' platform, but AfterShip is primarily a post-purchase tracking/shipping experience platform, not a full ERP. This factual mismatch could mislead agents into recommending the wrong system-of-record boundaries.
• The skill depends on an AI-HIVE MCP being available and calls 'tools/list', but it does not document setup prerequisites such as connection details, authentication, environment variables, or fallback behavior when the MCP tools are unavailable.
• There is no explicit prompt-injection guardrail for external or generated content. AI-HIVE outputs and uploaded assets should always be treated as data, not as instructions to execute.
• The JSON contract mentions controls like sandbox and human approval but does not include concrete budget limits, timeouts, or stop conditions, even though budget and rollback are discussed in prose.
• Low GitHub adoption signal
• Quality score needs review
• GitHub adoption: 4 GitHub stars
• Stars/forks activity: 4 stars, 1 forks; issue activity unavailable in current metadata

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.