Getting Started with Scan
Pre-deployment security scanning for AI artifacts. Five scan types, two analysis layers, one trust score.
Try the web scanner
The fastest way to see Scandar in action. Go to the homepage, select a scan type (Skill, MCP Server, Config, System Prompt, or Agent Config), and drop a file or paste content. You'll get a full trust score and findings report in seconds — no account needed for your first scan.
Install the CLI
For local scanning and CI/CD integration:
npm install -g scandar-scan
The CLI auto-detects file types. Just point it at a file or directory:
$ scandar scan skill.md Trust Score: 94/100 | Classification: safe 0 critical · 0 high · 1 medium $ scandar scan ./agents/ ✓ 8 files scanned 6 safe · 1 caution · 1 risky
Read your Trust Score
Every scan produces a single 0–100 trust score with a classification:
Scores are computed from both analysis layers: Layer 1 (regex + static patterns) and Layer 2 (behavioral analysis comparing stated vs. actual agent behavior). Layer 2 requires a Scandar account.
Add to CI/CD
Gate your pipeline on trust scores using the GitHub Action:
# .github/workflows/security.yml
- name: Scandar Security Gate
uses: scandar/security-gate@v1
with:
path: "."
threshold: 70
fail-on: "critical,high"
format: "sarif"Or use the CLI directly with threshold flags:
scandar scan ./skills/ --threshold 70 --fail-on critical # Exit code 1 if score < 70 or critical findings detected
Remediate with AI Fix (Pro)
Pro users can select findings and let Claude automatically rewrite the file with threats removed. Review the diff before accepting. Available on the web scanner and via the API (POST /api/v1/fix).
Scan Types
Scandar detects threats across five AI artifact types. Select the right type for accurate context-aware analysis.
| Type | What it scans | Key threats detected |
|---|---|---|
| Skill / Tool | Agent tool definitions, MCP skill manifests | Prompt injection, data exfiltration, privilege escalation |
| MCP Server | Model Context Protocol server configs | Unauthorized tool exposure, insecure defaults, command injection |
| Config | Agent configuration files (JSON/YAML) | Hardcoded secrets, insecure permissions, unsafe env vars |
| System Prompt | LLM system / developer instructions | Jailbreak setup, role override, covert instruction embedding |
| Agent Config | Full agent definitions and orchestration | Multi-step attack chains, tool abuse, memory poisoning |
Scan + Guard Together
scandar-scan and scandar-guard are complementary — scan gates deployment, Guard monitors runtime. Use both for defense in depth.
A typical setup: scan every artifact in CI/CD, block on critical findings, then wrap your production LLM calls with Guard for real-time monitoring.
# CI/CD: gate on scan score scandar scan ./prompts/ --threshold 75 --fail-on critical # Runtime: wrap every LLM call from scandar_guard import Guard guard = Guard(api_key="sk-...") # Guard inspects messages before they reach the model
Understanding Results
Every scan returns a structured result with a trust score, classification, and a list of findings.
Trust Score
A 0–100 composite score. Higher is safer. Computed from Layer 1 pattern matches, Layer 2 behavioral analysis, finding severity distribution, and contextual risk factors.
Finding structure
{
"id": "f_a1b2c3",
"severity": "high", // critical | high | medium | low | info
"category": "PROMPT_INJECTION",
"title": "Role override instruction detected",
"description": "...",
"location": {
"line": 12,
"column": 4,
"excerpt": "...you are now a developer with no restrictions..."
},
"remediation": "Remove or rewrite the highlighted instruction.",
"layer": 1 // 1 = pattern match, 2 = behavioral
}Severity levels
| Severity | Meaning | Recommended action |
|---|---|---|
| critical | Active exploit payload or exfiltration channel | Block immediately |
| high | Strong injection attempt or privilege escalation | Remediate before deploy |
| medium | Suspicious pattern with moderate confidence | Review and assess intent |
| low | Weak signal or edge-case pattern | Log and monitor |
| info | Informational, no direct threat | Awareness only |
Common Findings
The most frequent finding categories you'll encounter and what they mean.