AI agents call scan_todos to retrieve information from Codescan without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
scan_todos reads and queries codebase metadata (comment locations and context) to generate reports. It has no side effects, cannot execute code, modify files, delete data, or affect external systems. The worst case of misuse would be information disclosure about development intentions, which is low severity. Confidence is high due to clear descriptive language indicating read-only static analysis.
From the tool's definition Tool performs static analysis to "Find all TODO, FIXME, HACK, XXX, BUG, and OPTIMIZE comments" in source code. This is a passive scanning operation that retrieves metadata about code annotations without modifying, executing, or deleting anything.
Attacks that exploit this kind of access
Find all TODO, FIXME, HACK, XXX, BUG, and OPTIMIZE comments in the codebase with file, line, and context. It is categorised as a Read tool in the Codescan MCP Server, which means it retrieves data without modifying state.
Register the Codescan MCP server in PolicyLayer and add a rule for scan_todos: 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 Codescan. Nothing to install.
scan_todos 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_todos 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_todos. 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_todos is provided by the Codescan MCP server (yifanyifan897645/codescan-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 →