CrewAI crew with tools and no request limit
LowAV-FW-017Runtime safetyFramework packNew in 2.0
What it finds
A CrewAI crew whose agents have tools sets no max_rpm, max_iter or max_execution_time.
Why it matters
Crews can loop between agents. Without limits a single run can make a very large number of model and tool calls.
What an attacker could do: Runaway runs can spike cost and repeat side effects.
How to fix it
Set max_rpm on the crew and max_iter / max_execution_time on agents.
Pro shows the corrected code for your exact file, step by step, and re-scans to confirm the fix. See plans
Check details
- Finding code
- CREWAI_NO_MAX_RPM
- How it detects
- Looks for a risky pattern, and stays quiet when a matching safeguard is present.
- Confidence
- Likely: strong signal, but review it in context.
- Scans
- Agent source using the named framework (LangChain, CrewAI, AutoGen, OpenAI Agents SDK, Claude Agent SDK, computer-use tools)
- OWASP LLM Top 10
- LLM04 - Model Denial of Service
- NIST AI RMF
- MG-2.2
- SOC 2
- A1.1
Check your agent for this
Paste your agent code or MCP config. The free scan runs all 124 checks in about 10 seconds — no account needed.
Related checks
- Command injection riskAV-RUNTIME-004 · Critical
- Unsafe dynamic code executionAV-RUNTIME-005 · Critical
- Privileged or host-mounted container configurationAV-RUNTIME-007 · Critical
- SQL query built from unescaped inputAV-RUNTIME-009 · Critical
- Unsafe deserialization of untrusted dataAV-RUNTIME-010 · Critical
- Prompt injection surface detectedAV-RUNTIME-002 · High