Base Tx Preflight

Security checkA100/100

We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 6, 2026.

• Hidden or reordered text
• Overriding the model's instructions
• Hiding actions from the user
• Reading keys or credentials
• Fake system tags
• Steering other servers' tools
• Pulling in the conversation
• Smuggling parameters
• Demanding to be used for everything
• Steering away from web search
• Download-and-run commands
• Encoded blobs
• Invisible characters
• Credentials as tool arguments
• Very long descriptions
• Read and write hintsNote1 found

  No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.

  • server · annotations
    2 of 2 tools: preflight_quote, preflight_validate

  Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.