guardrail-middleware
Runtime authorization for AI agent tool calls. GuardRail sits between an AI agent and its tools: every proposed action is checked against a policy before it executes, and every decision is written to a tamper-evident audit log.
An agent that can call tools can also be talked into misusing them: by a prompt injection in an email, a poisoned webpage, or its own overconfidence. GuardRail is the checkpoint that asks, deterministically and in under a millisecond: is this role allowed to do this, to this resource, with these parameters, on the say-so of this source?
pip install guardrail-middleware # core, zero dependencies
pip install guardrail-middleware[fastapi] # + FastAPI/Starlette middleware
Quick start: framework-agnostic
from guardrail_middleware import Guardrail
guard = Guardrail() # built-in default policy
decision = guard.evaluate({
"tool": "payments",
"operation": "payment",
"target_resource": "vendor/acme",
"parameters": {"amount": 42000},
"agent_role": "support",
})
decision.verdict # Verdict.BLOCK (role 'support' may not run payments)
decision.allowed # False
decision.explanation
Works anywhere an agent proposes an action: LangChain/LangGraph tool wrappers, MCP servers, custom agent loops, job queues.
Tool names work as-is, too. If an action names only a tool, GuardRail classifies it from the name: send_payment, stripe_refund, delete_user and get_order_status are all understood (params is accepted as an alias for parameters, source_type for triggered_by).
Quick start: FastAPI / Starlette middleware
from fastapi import FastAPI
from guardrail_middleware import Guardrail, AuditLog
from guardrail_middleware.fastapi import GuardrailMiddleware
app = FastAPI()
app.add_middleware(
GuardrailMiddleware,
guard=Guardrail(audit_log=AuditLog("audit.jsonl")),
paths=["/tools/execute"],
)
Requests to guarded paths are read as actions. Blocked or escalated actions never reach your handler. The client gets HTTP 403 with the full decision as JSON. Allowed actions pass through with X-Guardrail-Verdict and X-Guardrail-Risk headers set.
Quick start: decorator
from guardrail_middleware.fastapi import guard_tool, GuardrailBlocked
@guard_tool(guard, tool="payments", operation="payment", agent_role="support")
def send_payment(amount: int, to: str):
... # only runs if GuardRail approves
try:
send_payment(amount=42_000, to="vendor/acme")
except GuardrailBlocked as stopped:
print(stopped.decision.explanation)
Verdicts
| Verdict | Meaning |
|---|---|
APPROVE |
No policy issues. Execute. |
APPROVE_WITH_CONDITIONS |
Execute only with the attached conditions (batch it, back up first, dry-run). |
ESCALATE_TO_HUMAN |
A person must approve first (over-limit payment, untrusted source, unbounded delete). |
BLOCK |
Never execute (injection, unauthorized role, PII exfiltration, hard money ceiling). |
Priority is fail-safe: any block finding wins, then escalate, then conditions.
What it checks: 7 deterministic detectors
No LLM in the decision path: the same action under the same policy always gets the same verdict, reproducibly and fast.
- Injection: instruction-override / role-hijack / secret-extraction / policy-bypass patterns in untrusted content (email, webpage, tool output). Untrusted content is data, never instructions.
- Authorization: role × operation-class permissions (an
internrole cannot delete, asupportrole cannot pay). - Financial limits: per-class auto-approve and block thresholds, plus a hard ceiling no role can exceed; a payment with no verifiable amount escalates.
- Bulk operations: record-count thresholds: conditions (batch + dry-run) above the auto-approve max, escalation above the bulk ceiling.
- Taint / exfiltration: PII or secret fields flowing to an external destination is blocked; secrets inside tool-call parameters are blocked outright.
- Destructive actions: irreversible operations without a backup/confirmation marker get conditions; a delete with no target escalates.
- Untrusted source: money movement, deletion, or external sends triggered by email/webpage/tool-output content escalate to a human.
Policy
Every threshold lives in one policy dict. Tune it without touching code, or load it from YAML:
from guardrail_middleware import Guardrail, Policy
policy = Policy.from_yaml("policy.yaml") # see policy.example.yaml
guard = Guardrail(policy=policy)
# …or inline
guard = Guardrail(policy={"approval_limits": {"payment": {"auto_approve_max": 500}}})
Audit log
Pass an AuditLog and every decision is appended as one JSON line, hash-chained with SHA-256: each entry commits to the previous entry's hash, so editing, deleting, or reordering history breaks the chain.
from guardrail_middleware import AuditLog
AuditLog("audit.jsonl").verify() # {'ok': True, 'entries': 128, 'broken_at': None}
Demo & tests
python examples/demo.py # 5 scenarios, all four verdicts, audit verification
pytest # 20 tests: engine, detectors, middleware, decorator, audit tampering
Where this comes from
guardrail-middleware is the reusable enforcement core extracted from GuardRail, a runtime action-authorization and behavioral-safety layer for agentic AI built at Infosys Ignite EngNext 2026 (special recognition), where the full system adds multi-step plan validation, an action-passport execution gateway, and a 42-scenario adversarial red-team benchmark. It packages the single-action checkpoint from that system so any agent stack can adopt it in minutes.
Status & honesty notes
- v0.1.1, alpha. The API may still move.
- Detectors are deterministic heuristics, not a proof of safety. Pair them with least-privilege credentials and human review for high-impact tools.
- Plan-level (multi-step) validation lives in the main GuardRail project, not in this package yet.
License
MIT © Niraj Sanjay Karnawat
Metadata
Release files for guardrail-middleware 0.1.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| guardrail_middleware-0.1.1.tar.gz | 20.6 kB | With provenance | Details for guardrail_middleware-0.1.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| guardrail_middleware-0.1.1-py3-none-any.whl | Python 3 | none | any | Details for guardrail_middleware-0.1.1-py3-none-any.whl |
Total release size: 40.1 kB
Release files / guardrail_middleware-0.1.1.tar.gz
| Download URL | guardrail_middleware-0.1.1.tar.gz |
|---|---|
| Size | 20.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
72d9d5e3145a834b7da5258ec2220fbceb48af624d5931c8db914a1f5638bca5
|
|
BLAKE2b-256 checksum How to use checksums |
b08ddb31b627304010e3186e80dcd8a89786473f4189b8dd444161abab3c9861
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 18, 2026.
Transparency logRelease files / guardrail_middleware-0.1.1-py3-none-any.whl
| Download URL | guardrail_middleware-0.1.1-py3-none-any.whl |
|---|---|
| Size | 19.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
e0b0a8eea86cfe26f0cce28c9408a03d271aa230b372e31c707d4cc8e9560cd2
|
|
BLAKE2b-256 checksum How to use checksums |
16ccda0940c22c9744888bb19e3eb522bb6ee455023544efad64cdaa5d94c705
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 18, 2026.
Transparency logSecurity for guardrail-middleware 0.1.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
Full provenance
Both files in this release have been uploaded with provenance metadata.
Attestation for guardrail_middleware-0.1.1.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 18, 2026.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.