Tool arguments used without validation
MediumAV-TOOL-002ToolsCore packNew in 2.0
What it finds
Tool-call arguments from the model are parsed and used directly, with no schema validation.
Why it matters
Model output is untrusted. Missing or unexpected fields, wrong types, or injected values flow straight into your tool code.
What an attacker could do: Malformed or malicious arguments reach tool logic unchecked.
How to fix it
Validate arguments with a schema (zod, pydantic, JSON Schema) and reject anything that does not match.
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
- TOOL_ARGS_NOT_VALIDATED
- How it detects
- Looks for a risky pattern, and stays quiet when a matching safeguard is present.
- 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, LLM07 - Insecure Plugin Design
- 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.