Tool or web results placed in the system prompt
HighAV-RUNTIME-019Runtime safetyCore packNew in 2.0
What it finds
Content from tools, web pages, search results or emails is inserted into the system message.
Why it matters
Models give the system message the most authority. Untrusted text placed there is the easiest possible prompt injection.
What an attacker could do: A web page or email could take over the agent's instructions.
How to fix it
Keep the system prompt fixed. Put tool and retrieved content in user or tool messages, clearly marked 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
- TOOL_RESULT_AS_SYSTEM_PROMPT
- 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
- LLM01 - Prompt Injection
- 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