pip-audit
Runs pip-audit and returns a structured vulnerability report.
This record as markdown: /tools/io-github-dave-london-docker/pip-audit.md
What pip-audit does on Docker
AI agents call pip-audit to retrieve information from Docker without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why pip-audit is rated Low
pip-audit is a read-only vulnerability scanning tool. It queries package metadata and vulnerability databases to generate a report, with no capability to modify, delete, or execute code. While it does trigger an external operation (pip-audit execution), the operation is intrinsically informational and deterministic—it scans and reports vulnerabilities without side effects on the system state.
From the tool's definition Tool name: pip-audit. Description: 'Runs pip-audit and returns a structured vulnerability report.' The tool executes pip-audit, a Python dependency scanner that analyzes installed packages for known vulnerabilities and returns findings in a structured format.
Attacks that exploit this kind of access
The rule that runs pip-audit safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Docker, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For pip-audit, this is the rule to start with:
pip-audit is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Docker, apply this rule, and every pip-audit call is checked against it from then on.
Questions about pip-audit
Runs pip-audit and returns a structured vulnerability report. It is categorised as a Read tool in the Docker MCP Server, which means it retrieves data without modifying state.
Register the Docker MCP server in PolicyLayer and add a rule for pip-audit: 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 Docker. Nothing to install.
pip-audit 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 pip-audit 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 pip-audit. 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.
pip-audit is provided by the Docker MCP server (@paretools/docker). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Docker, and thousands of servers like it.
This server
Across the catalogue