get_program_slice
AI agents call get_program_slice 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.
Program slicing in static analysis retrieves code segments or dataflow information relevant to a query without modifying source code or executing it. This is a read operation with minimal security risk—the tool cannot execute code, modify files, or trigger external actions. The empty description reduces confidence slightly, but context from sibling tools and the name strongly indicate a read-only analysis function.
From the tool's definition Tool name 'get_program_slice' and server context indicate data retrieval from code analysis. The CodeBadger server performs static analysis using Joern's Code Property Graph, and sibling tools like 'find_taint_sinks', 'find_taint_sources', and…
Attacks that exploit this kind of access
get_program_slice. 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 get_program_slice: 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.
get_program_slice 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 get_program_slice 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 get_program_slice. 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.
get_program_slice 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 →