The Autonomous Stack

AI Security & LLM Ops · LLM Security · v1.0.0

PromptShield Agent v1.0

Offline-first prompt-injection hygiene for LLM input pipelines.

$3.00one-timePay with crypto

llm-security prompt-injection offline governance

agent ⟶ theautonomousstack.xyz

01GET /api/v1/pack/agent-promptshield-v1

402 Payment RequiredX-PAYMENT-REQUIRED

02sign TransferWithAuthorization3.00 USDC · Base (eip155:8453)

03GET + PAYMENT-SIGNATURE

200 OKapplication/zip · 19 files

pay per pack over x402no account

What's inside

PromptShield is an offline-first prompt-injection hygiene agent for teams running LLM workflows. It scans untrusted text and instruction repositories, explains deterministic matches, and produces a review queue. It never executes a discovered instruction, calls a model, or changes source files.

It is for LLM operators who ingest tickets, documents, web pages, emails, or connector payloads and need a repeatable preflight check before those texts reach an agent.

Quick start

./install.sh                                    # one-shot, stdlib only, offline
python3 agent.py --help

# Two fixtures ship with the pack: one benign ticket, one carrying an injection.
python3 agent.py scan --input examples/clean_ticket.txt      # verdict: clean,  exit 0
python3 agent.py scan --input examples/hostile_ticket.txt \
    --output promptshield-report.json --fail-on high         # verdict: review, exit 2

bash smoke_test.sh runs 16 end-to-end checks offline; bash deploy.sh (root) installs the systemd unit and an hourly timer.

untrusted input -> normalize -> deterministic rules -> findings -> review report
                                      |                         |
                                      +---- optional BYO-LLM ---+ (never required)

scan is deliberately conservative: a finding is evidence for review, not proof of malice. Use --fail-on high in a CI or ingestion gate. No API key is needed; the optional local Claude/Kimi/Codex adapter is only used by explain when explicitly requested.

Safety boundary

The pack reads local files only. It does not fetch URLs, send data, execute embedded commands, or redact/mutate an input. Keep secrets out of sample files and review high-severity findings before blocking a workflow.

See CHECKLIST.md for rollout, CUSTOMIZE.md for rules and integrations, and SPEC.md for the stable JSON contract.