Scans the repository for files that SHOULD be ignored but aren't,
AI agents call audit_gitignore to retrieve information from GitHub Auditor MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a read-only scan to identify files that should be gitignored but currently are not. It retrieves and reports findings without modifying, deleting, or executing anything. Severity is medium because the results could expose sensitive file paths or inadvertently tracked secrets, but the tool itself only reads.
From the tool's definition 'Scans the repository for files that SHOULD be ignored but aren't' — this is a scanning/discovery operation with no stated side effects
Attacks that exploit this kind of access
Scans the repository for files that SHOULD be ignored but aren't,. It is categorised as a Read tool in the GitHub Auditor MCP Server MCP Server, which means it retrieves data without modifying state.
Register the GitHub Auditor MCP Server MCP server in PolicyLayer and add a rule for audit_gitignore: 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 GitHub Auditor MCP Server. Nothing to install.
audit_gitignore 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 audit_gitignore 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 audit_gitignore. 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.
audit_gitignore is provided by the GitHub Auditor MCP Server MCP server (westkevin12/repo-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 →