Cloakwall

PII/PHI redaction and tamper-evident audit logging for LiteLLM. Runs in-process — no sidecar container, no external endpoint, no model download.

LiteLLM's open-source guardrail framework supports custom guardrails plus Presidio, but Presidio means deploying and maintaining two extra containers, and audit logs, SIEM export and SSO sit behind the Enterprise licence. Cloakwall gives you redaction and a compliance-grade audit trail as one dependency-free plugin.

guardrails:
  - guardrail_name: cloakwall
    litellm_params:
      guardrail: cloakwall.guardrail.Cloakwall
      mode: pre_call
      default_on: true
      redaction_mode: mask
      audit_path: /var/log/cloakwall/audit.log

To mask PII in model responses as well, add redact_output: true and set mode: [pre_call, post_call].

user:  "Patient MRN: A1234567, email bob@clinic.org, card 4111111111111111"
model: "Patient <MRN>, email <EMAIL>, card <CARD>"

Install

pip install "cloakwall[litellm]"

LiteLLM refuses to start without a master key (an API key for the proxy itself), so set one, then point LiteLLM at a config that enables the guardrail, such as examples/config.yaml:

export LITELLM_MASTER_KEY="sk-$(openssl rand -hex 32)"
litellm --config config.yaml

Clients then call the proxy with Authorization: Bearer $LITELLM_MASTER_KEY.

Or run the container, which installs the same package from PyPI:

docker build -t cloakwall .
docker run -p 4000:4000 \
  -e LITELLM_MASTER_KEY="sk-$(openssl rand -hex 32)" \
  -e OPENAI_API_KEY=sk-... cloakwall

Run it on Linux in production. The audit log fsyncs every entry; that costs about 0.3 ms on Linux and about 100 ms on Windows (see Benchmarks).

Where it looks

Every request field LiteLLM forwards that can carry text, on every endpoint:

Image, audio and file parts pass through untouched. Ids, roles, model names and function names are never rewritten.

With redact_output: true, responses are redacted too: chat content and tool-call arguments, text completions, and Anthropic content blocks. Streamed responses go through a stream redactor that holds back the last 64 characters (stream_holdback) and only releases text at a boundary no entity spans, so a card number split across two chunks is still caught. The cost is that streamed text reaches the client 64 characters later; none of it is dropped. Output redaction is off by default, because it changes what callers receive.

Three redaction modes

hash is deterministic under a local HMAC secret set with CLOAKWALL_SECRET. Same person, same token, every request. Without a secret one is generated per boot, so tokens are stable within a run only.

Audit trail

Every entry commits to the SHA-256 of the entry before it and carries a monotonic sequence number. The chain head is mirrored to a separate anchor file after every append, and pushed to your SIEM every anchor_every entries.

That combination catches all four tamper modes:

chain intact, 10 entries, anchor matches
line 2: entry altered after writing
line 3: chain break
truncated: anchor records 10 entries, log holds 6

The last one is why the anchor exists. A bare hash chain does not survive truncation — a prefix of a valid chain is itself a valid chain, so dropping the final entries verifies clean. The anchor still knows how many there should be.

An anchor on the same filesystem stops accidental truncation and a careless attacker. An anchor in your SIEM, under different access control, stops someone who can write to the pod. Pass a SIEM-retrieved anchor to verify(anchor=...) to check against a copy the log cannot reach.

The log records which entity types were found and how many. It never records the values that were redacted — an audit log that quotes the PII it scrubbed is a second copy of the problem.

SIEM export

export CLOAKWALL_SIEM=splunk          # splunk | datadog | elastic
export CLOAKWALL_SIEM_URL=https://splunk.internal:8088/services/collector
export CLOAKWALL_SIEM_TOKEN=...

Export runs on a worker thread. A slow or unreachable SIEM never adds latency to, or fails, an LLM request — the local log is the system of record.

Air-gapped

The core is pure standard library. Nothing in the redaction, audit or hashing path opens a socket, so it runs unchanged in an isolated cluster. Point LiteLLM at a local vLLM or Ollama endpoint and no data leaves your network at all.

Verify it yourself:

strace -f -e trace=connect python3 tests/test_cloakwall.py

Benchmarks

Measured, reproducible numbers are in BENCHMARKS.md: python3 benchmarks/bench.py. On a 2015 Core i3 under Linux, a clean request costs 0.05 ms and a request with PII, including its fsynced audit entry, about 1.8 ms.

Tests

python3 tests/test_cloakwall.py     # 76 tests, no pytest required

Limitations

Regex detection does not catch contextual PII — a person's name in free text, or a medical condition described in prose. If you need that, Presidio's NLP models are better and Cloakwall is not a replacement for them. What Cloakwall gives up in recall it gains in having no dependencies, no sidecar and no model to ship into an air-gapped environment.

Redaction is one-way. There is no un-redaction path, by design.

Status: working, tested, not yet run in production anywhere.

Security

Found a vulnerability, or a way PII gets past the redactor? Please report it privately; see SECURITY.md.

Licence

AGPL-3.0. Commercial licences for closed-source use are available.