Server-side template built from user or model text
HighAV-RUNTIME-017Runtime safetyCore packNew in 2.0
What it finds
A template engine compiles text that came from a user or the model.
Why it matters
Template languages can run code. If an attacker controls the template text (directly or through prompt injection) they can execute code on the server.
What an attacker could do: Remote code execution on the server.
How to fix it
Never compile untrusted text as a template. Use a fixed template and pass the text in as data.
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
- TEMPLATE_INJECTION
- How it detects
- Looks for a specific risky pattern in the code or config.
- Confidence
- Likely: strong signal, but review it in context.
- Scans
- Any text-based agent source or configuration (JS/TS/Python/JSON/YAML)
- OWASP LLM Top 10
- LLM02 - Insecure Output Handling
- NIST AI RMF
- MS-2.3
- SOC 2
- CC7.1
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