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 t...
Accepts freeform code/query input (command); Accepts file system path (working_directory)
Part of the Shrike Security MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
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.
tools:
scan_command:
rules:
- action: allowSee the full Shrike Security policy for all 12 tools.
Agents calling read-class tools like scan_command have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
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 (curl -d @file, scp to remote, pipe chains like cat .env | curl) - Destructive operations (rm -rf /, dd to device, mkfs) - Remote code execution (reverse shells, curl | sh, nc -e) - Privilege escalation (chmod u+s, sudoers modification) - Secret exposure (cat .env, echo $API_KEY, reading credentials files) - Obfuscated commands (base64 decode | sh, eval with expansion) - Pipe chain analysis (cross-command threat detection for individually safe commands) 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.
Add a rule in your Intercept YAML policy under the tools section for scan_command. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Shrike Security MCP server.
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 Intercept 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 Intercept 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). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept