First Seen
Feb 18, 2026
Last Scanned
Feb 22, 2026
Findings
2
Score
85/100
Findings (2)
Detects instructions to hide actions from the user
Do NOT show the raw JSON response to the user Remove directives that attempt to change the agent's output format, suppress safety warnings, or alter response structure in ways that bypass safety controls.
Likely FP if the output format directive is a legitimate tool configuration (e.g., return results as JSON) that does not suppress safety features.
Detects MCP server configurations connecting to non-localhost remote URLs
"url": "https://x.com/.../status/..." Change the MCP server URL to localhost or a trusted internal endpoint. If a remote server is required, verify the domain ownership and use HTTPS with certificate validation.
Likely FP if the URL points to example.com, a documentation domain, or a well-known SaaS API endpoint (e.g., api.openai.com).