Destructive tool with no confirmation
HighAV-HUMAN-004Human oversightCore packNew in 2.0
What it finds
The agent has a tool that deletes, drops, wipes or terminates things, and nothing asks a person first.
Why it matters
Deletions are usually permanent. A misunderstanding or an injected instruction is enough to lose data or shut down systems.
What an attacker could do: The agent can permanently delete data or resources on its own.
How to fix it
Require explicit human confirmation for destructive tools, prefer soft-delete, and support a dry-run mode.
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
- DESTRUCTIVE_TOOL_NO_CONFIRM
- 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
- LLM08 - Excessive Agency
- NIST AI RMF
- MG-2.2
- SOC 2
- CC6.1, CC8.1
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
- Agent can move money with no amount limitAV-HUMAN-003 · Critical
- Missing human-in-the-loop gatesAV-HUMAN-001 · High
- Built-in safety controls turned offAV-HUMAN-002 · High
- AI editor set to run every tool without askingAV-FW-013 · High
- OpenAI Agents SDK agent with tools but no guardrailsAV-FW-006 · Medium
- MCP tools set to run without askingAV-MCP-104 · Medium