First Seen
Feb 18, 2026
Last Scanned
Feb 22, 2026
Findings
7
Score
92/100
Findings (7)
Detects instructions to hide actions from the user
Never share userRemove 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://my-agent.example.com/a2a"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).
Detects MCP server configurations connecting to non-localhost remote URLs
"url": "https://my-agent.example.com"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).
Detects MCP server configurations connecting to non-localhost remote URLs
"url": "https://my-agent.example.com/mcp"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).
Detects URLs fetched at runtime that control or influence agent behavior without pinning
Fetch the heartbeat guide: `curl -s https:// + promptAvoid loading configuration or behavior-controlling content from runtime URLs. Bundle required configurations locally or pin remote config to versioned, integrity-verified endpoints.
Likely FP if the URL in the match is a documentation link or example URL (e.g., example.com) rather than an actual runtime-fetched configuration endpoint.
Detects npx with -y flag that bypasses user confirmation for package installation
npx -y Replace npx -y with an explicit npm install step that pins the package to a specific version, then run it. Remove the -y flag to require user confirmation.
Likely FP if the npx command runs a well-known, trusted tool (e.g., create-react-app) in documentation context with no version pinning concern.
Detects npx with -y flag that bypasses user confirmation for package installation
npx -y Replace npx -y with an explicit npm install step that pins the package to a specific version, then run it. Remove the -y flag to require user confirmation.
Likely FP if the npx command runs a well-known, trusted tool (e.g., create-react-app) in documentation context with no version pinning concern.