CrewAI
Security Scanner
Framework for orchestrating role-playing AI agents. Detects delegation loops and task dependencies.
What Inkog Detects in CrewAI
CrewAI-specific vulnerability patterns that traditional security tools miss.
Infinite Loop Detection
CRITICALCrewAI agents without iteration bounds can run indefinitely, consuming API tokens until limits are hit.
Prompt Injection Paths
CRITICALUser inputs flowing to LLM prompts without sanitization in CrewAI workflows create injection vulnerabilities.
Token Bombing
HIGHUnbounded loops in CrewAI agents accumulate LLM API costs that can reach thousands of dollars.
Missing Human Oversight
HIGHHigh-risk tool calls in CrewAI agents without human approval gates violate EU AI Act Article 14.
CrewAI Analysis Features
- Agent delegation loop detection
- Task dependency analysis
- Crew orchestration validation
- Tool permission checks
Get Started
Scan your CrewAI application in seconds.
Run the scanner
inkog scan ./my-crewai-appReview findings
Inkog traces data flow through your CrewAI code and reports vulnerabilities with severity levels and line numbers.
Fix and verify
Apply the suggested fixes based on severity and re-scan to verify.
CrewAI Compliance Reports
Automated mapping to global AI governance frameworks.
EU AI Act
Article 14, 15, 12
NIST AI RMF
MAP/MEASURE/MANAGE
OWASP LLM
Top 10 Coverage
ISO 42001
AI Management
Related Integrations
Scan Your CrewAI Application
Free for developers. Results in 60 seconds.