Free. TensorFeed's deploy gate for an AI software stack: pass each package name (comma-separated name@version) and get the overall BLOCK / HOLD / PASS / UNKNOWN gate plus a per-package verdict, fusing the ingested AI-stack CVE batch with the CISA KEV catalog. Conservative by design: BLOCK only on...
Part of the TensorFeed server.
Free to start. No card required.
AI agents invoke stack_safety_verdict_preview to trigger processes or run actions in TensorFeed. Execute operations can have side effects beyond the immediate call -- triggering builds, sending notifications, or starting workflows. Rate limits and argument validation are essential to prevent runaway execution.
stack_safety_verdict_preview can trigger processes with real-world consequences. An uncontrolled agent might start dozens of builds, send mass notifications, or kick off expensive compute jobs. PolicyLayer enforces rate limits and validates arguments to keep execution within safe bounds.
Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.
{
"version": "1",
"default": "deny",
"tools": {
"stack_safety_verdict_preview": {
"limits": [
{
"counter": "stack_safety_verdict_preview_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}See the full TensorFeed policy for all 79 tools.
These attack patterns abuse exactly the kind of access stack_safety_verdict_preview gives an agent. Each links to the full case and the policy that stops it:
Other execute tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Free. TensorFeed's deploy gate for an AI software stack: pass each package name (comma-separated name@version) and get the overall BLOCK / HOLD / PASS / UNKNOWN gate plus a per-package verdict, fusing the ingested AI-stack CVE batch with the CISA KEV catalog. Conservative by design: BLOCK only on an exploited CVE with no fix, HOLD when a known CVE applies and you must verify your version, PASS on no match, UNKNOWN outside the curated AI-stack cohort. For the matched-CVE evidence (ids, ranges, fixes, KEV status), up to 10 packages, and an AFTA-signed receipt, use stack_safety_verdict. Capped at 3 packages, 10 calls per day per IP.. It is categorised as a Execute tool in the TensorFeed MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the TensorFeed MCP server in PolicyLayer and add a rule for stack_safety_verdict_preview: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches TensorFeed. Nothing to install.
stack_safety_verdict_preview is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the stack_safety_verdict_preview rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for stack_safety_verdict_preview. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
stack_safety_verdict_preview is provided by the TensorFeed MCP server (https://mcp.tensorfeed.ai/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 79 TensorFeed tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.