외부에서 받아온 SKILL.md 본문을 설치 전에 정적 검증합니다(설치 안 함).
AI agents call db_skill_scan to retrieve information from K-Personal MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool scans and validates file content without executing installation or making any changes to the system. It is a read-only inspection operation. The low severity reflects the minimal blast radius: even if misused, static validation on content prior to installation poses no direct harm to system state or data.
From the tool's definition Tool description states it performs 'static validation' of externally received SKILL.md content 'before installation (does not install)'. The verb 'validates' and explicit statement that it 'does not install' indicate no side effects or modifications occur.
Attacks that exploit this kind of access
외부에서 받아온 SKILL.md 본문을 설치 전에 정적 검증합니다(설치 안 함). It is categorised as a Read tool in the K-Personal MCP MCP Server, which means it retrieves data without modifying state.
Register the K-Personal MCP server in PolicyLayer and add a rule for db_skill_scan: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches K-Personal MCP. Nothing to install.
db_skill_scan is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the db_skill_scan rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for db_skill_scan. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
db_skill_scan is provided by the K-Personal MCP server (lee30934-byte/k-personal-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →