find_taint_sources
AI agents call find_taint_sources to retrieve information from CodeBadger without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs static code analysis to locate potential taint sources—a security analysis capability that queries the Code Property Graph to identify data sources without modifying code or triggering side effects. Despite empty description, the naming and context (security taint analysis suite) confirm it retrieves/queries code properties rather than executing, writing, or deleting.
From the tool's definition Tool name 'find_taint_sources' indicates identification/detection of taint sources in code. No description provided, but naming pattern matches sibling security analysis tools (find_taint_sinks, find_double_free, etc.) which are read-only code analysis…
Attacks that exploit this kind of access
find_taint_sources. It is categorised as a Read tool in the CodeBadger MCP Server, which means it retrieves data without modifying state.
Register the CodeBadger MCP server in PolicyLayer and add a rule for find_taint_sources: 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 CodeBadger. Nothing to install.
find_taint_sources 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 find_taint_sources 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 find_taint_sources. 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.
find_taint_sources is provided by the CodeBadger MCP server (lekssays/codebadger). 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 →