package.json, requirements.txt 등에서 취약한 의존성 검사
AI agents call scan-dependencies to retrieve information from Security Scanner MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs vulnerability scanning by reading and analyzing dependency manifests. While it identifies security issues, it does not write, execute external code, delete data, or move money. The severity is medium because the scan results inform security decisions but the tool itself only reads/analyzes existing dependency files.
From the tool's definition Tool scans dependency files (package.json, requirements.txt) to detect vulnerable dependencies. The description indicates inspection and detection of vulnerabilities without modifying files or executing code—purely analytical reading of dependency metadata.
Attacks that exploit this kind of access
package.json, requirements.txt 등에서 취약한 의존성 검사. It is categorised as a Read tool in the Security Scanner MCP MCP Server, which means it retrieves data without modifying state.
Register the Security Scanner MCP server in PolicyLayer and add a rule for scan-dependencies: 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 Security Scanner MCP. Nothing to install.
scan-dependencies 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 scan-dependencies 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 scan-dependencies. 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.
scan-dependencies is provided by the Security Scanner MCP server (ongjin/security-scanner-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
scan-dependencies is one line of Security Scanner's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →