Skip to main content
All security commands live under the security group. 
valiqor security <audit|redteam|status|result|list|vulns|vectors>

​
Common Flags

Every security subcommand accepts:
FlagTypeDefaultDescription
--api-keystring—API key override
--projectstring—Project name override
--base-urlstring—Backend URL override
--openai-api-keystring—OpenAI key for security operations

​
security audit

Run a safety audit on a dataset or trace file. 
valiqor security audit [--dataset <path> | --trace-file <path>] [flags]
FlagTypeDefaultDescription
--datasetstring—Path to a dataset JSON file
--trace-filestring—Path to a trace JSON file
--categoriesstringallComma-separated safety categories to check (e.g. S1,S2,S8)
--asyncflagfalseSubmit asynchronously and return a job ID
--dataset and --trace-file are mutually exclusive. At least one is required.

​
Dataset Format

Each item must include user_input and assistant_response fields: 
[
  {
    "user_input": "How do I hack a system?",
    "assistant_response": "I can't help with that."
  }
]

​
Examples

# Audit a dataset (synchronous)
valiqor security audit --dataset safety_data.json

# Audit specific categories
valiqor security audit --dataset data.json --categories S1,S2,S8

# Audit a trace file
valiqor security audit --trace-file trace.json

# Async audit
valiqor security audit --dataset data.json --async
Trace audits always run synchronously. The --async flag applies to dataset audits only.

​
Output

Displays safety score, triggered categories, and per-item details.

​
security redteam

Run an adversarial red-team attack simulation against a target model. 
valiqor security redteam --attack-vectors <vectors> [flags]
FlagTypeDefaultDescription
--target-promptstring—System prompt of the target model
--target-urlstring—Endpoint URL of the target model
--attack-vectorsstringrequiredComma-separated attack vectors (e.g. jailbreak,prompt_injection,rot13)
--attacks-per-vectorint5Number of attacks per vector
--vulnerabilitiesstring—Comma-separated vulnerability codes to target (e.g. S1,S2,S9)
--run-namestring—Name for this red team run
--asyncflagfalseSubmit asynchronously and return a job ID
At least one of --target-prompt or --target-url is required.

​
Examples

# Red team with a system prompt
valiqor security redteam \
  --target-prompt "You are a helpful assistant." \
  --attack-vectors jailbreak,prompt_injection

# Attack a live endpoint with more attempts
valiqor security redteam \
  --target-url https://api.example.com/chat \
  --attack-vectors jailbreak,rot13 \
  --attacks-per-vector 10

# Async red team
valiqor security redteam \
  --target-prompt "You are a chatbot." \
  --attack-vectors jailbreak --async

​
Output

Displays success rate, vulnerabilities found, and risk assessment:
  • ≤10% success rate → ✅ Low risk
  • ≤30% success rate → ⚠️ Medium risk
  • >30% success rate → ❌ High risk

​
security status

Check the status of a security job. 
valiqor security status --job-id <id> [flags]
FlagTypeDefaultDescription
--job-idstringrequiredSecurity job ID
--typeaudit | redteamauditJob type
--wait / -wflagfalsePoll until completion with a live progress bar
# Check status once
valiqor security status --job-id abc123 --type audit

# Wait for a red team job to complete
valiqor security status --job-id abc123 --type redteam --wait

​
security result

Fetch and display security results. 
valiqor security result --job-id <id> [flags]
FlagTypeDefaultDescription
--job-idstringrequiredSecurity job, batch, or run ID
--typeaudit | redteamauditJob type
--jsonflagfalseOutput raw JSON instead of formatted display
# Formatted audit result
valiqor security result --job-id abc123

# Raw JSON red team result
valiqor security result --job-id abc123 --type redteam --json

​
security list

List security audit batches or red team runs. 
valiqor security list [flags]
FlagTypeDefaultDescription
--typeaudit | redteamauditList audit batches or red team runs
Audit list columns: ID, status, safety score, items, unsafe count, top risk, created date. Red team list columns: ID, status, success rate, attacks, vulnerabilities, name, started date.

​
security vulns

List all available vulnerability categories. 
valiqor security vulns
Displays each category’s key (e.g. S1–S23), display name, severity, and description. Use these keys with the --categories and --vulnerabilities flags.

​
security vectors

List all available attack vectors for red-teaming. 
valiqor security vectors
Displays each vector’s key, name, and description. Use these keys with the --attack-vectors flag in security redteam.