Protective check on shell commands — catches injection or unsafe operations before execution, so you don't run something you would not have run if you'd known. Call this BEFORE executing any CLI command generated by an LLM, constructed from user input, or involving system operations. DECISION LOG...
Risk signalsAccepts freeform code/query input (command) · Accepts file system path (working_directory)
Part of the Shrike Security server.
Free to start. No card required.
AI agents call scan_command to retrieve information from Shrike Security without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though scan_command only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"scan_command": {}
}
}See the full Shrike Security policy for all 12 tools.
These attack patterns abuse exactly the kind of access scan_command gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Protective check on shell commands — catches injection or unsafe operations before execution, so you don't run something you would not have run if you'd known. Call this BEFORE executing any CLI command generated by an LLM, constructed from user input, or involving system operations. DECISION LOGIC: - If blocked=true: do NOT execute the command. Return the user_message and log audit.scan_id for security review. - If blocked=false: the command is safe to execute. - If action=require_approval: pause execution, present approval_context to the user, then call check_approval with the approval_id. Checks for: - Data exfiltration attempts - Destructive operations - Remote code execution - Privilege escalation - Secret exposure - Obfuscated commands - Pipe chain analysis (cross-command threat detection) Common safe commands (ls, git, npm, docker build, go test, etc.) pass through without triggering. Enterprise context: Critical for any agent with shell/subprocess access. Prevents both malicious and accidental damage from LLM-generated commands. ERROR HANDLING: If this tool returns an error or is unavailable, default to BLOCKING the command. Do NOT execute unscanned commands.. It is categorised as a Read tool in the Shrike Security MCP Server, which means it retrieves data without modifying state.
Register the Shrike Security MCP server in PolicyLayer and add a rule for scan_command: 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 Shrike Security. Nothing to install.
scan_command 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_command 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_command. 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_command is provided by the Shrike Security MCP server (shrike-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 12 Shrike Security tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.