ada-ai-service-layer Audit report.

Warnings

• SKILL.md lacks an explicit setup/prerequisites section describing how to connect and authenticate to the AI-HIVE MCP service, what environment variables are needed, and which permissions the agent should have.
• Prohibited actions are clearly listed, but the skill could more explicitly enumerate forbidden MCP tools rather than relying only on the generic tools/list discovery and business contract.
• The pilot plan does not include an explicit budget check before creating paid media tasks, so cost overruns are possible if the agent is given broad autonomy.
• 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.