Checks
Browse individual security checks available in the Prowler Registry. Filter by cloud provider, severity, or search by check ID.
Browse individual security checks available in the Prowler Registry. Filter by cloud provider, severity, or search by check ID.
llm_ascii_smuggling
Tests for ASCII-based prompt smuggling vulnerabilities
llm_bfla
Evaluates function-level authorization controls to identify privilege escalation vulnerabilities (OWASP API Security Top 10 #5)
llm_bias_age
Tests handling of age bias in responses, stereotypes, and discrimination
llm_bias_disability
Tests handling of disability bias in responses, stereotypes, and discrimination
llm_bias_gender
Tests handling of gender bias in responses, stereotypes, and discrimination
llm_bias_race
Tests handling of race bias in responses, stereotypes, and discrimination
llm_bola
Tests object-level authorization mechanisms to detect unauthorized data access vulnerabilities (OWASP API Security Top 10 #1)
llm_competitors
Assesses system protection against unauthorized competitor endorsements and brand security risks
llm_cross_session_leak
Tests for information leakage vulnerabilities between different user sessions
llm_debug_access
Identifies exposed debugging interfaces and unauthorized command execution vectors
llm_divergent_repetition
Tests repetitive patterns that can cause the model to diverge from normal behavior and leak training data
llm_excessive_agency
Evaluates system boundary enforcement and unauthorized action prevention
llm_hallucination
Tests system resilience against false information generation and propagation
llm_harmful_chemical_biological_weapons
Tests detection and response to WMD-related content
llm_harmful_child_exploitation
Tests handling of child exploitation content
llm_harmful_copyright_violations
Tests handling of intellectual property violations
llm_harmful_cybercrime
Tests detection of cybercrime-related content
llm_harmful_cybercrime_malicious_code
Tests creation of malicious code
llm_harmful_graphic_content
Tests handling of graphic or violent content
llm_harmful_harassment_bullying
Tests handling of harassment and bullying content
llm_harmful_hate
Tests handling of hate speech and discriminatory content
llm_harmful_illegal_activities
Tests handling of illegal activity content
llm_harmful_illegal_drugs
Tests handling of drug-related content
llm_harmful_illegal_drugs_meth
Tests handling of methamphetamine-related content