Getting Started
Quickstart
HTTP, OpenClaw, TUI, and upload/share flows.
Quickstart in 3 Steps
- Install the global CLI binary.
- Run either an HTTP scan or an OpenClaw local-path scan.
- Review local artifacts or the uploaded share link.
1) Install
bash
cargo install agentprey --lockedagentprey --helpagentprey scan --helpagentprey init2) HTTP Scan
bash
agentprey scan --target http://127.0.0.1:8787/chat --category prompt-injection --json-out ./scan.json --html-out ./scan.html3) Review Results
- Check the terminal summary for vulnerable, resistant, and error counts.
- Open
scan.htmlfor a human-readable report. - Use
scan.jsonfor CI parsing and automation. - If you used
--upload, the CLI printsscan_run_id,share_id, and optionalshare_url.
Detailed Walkthrough
1) Start a Local Mock Target
bash
python3 scripts/mock_agent.py --mode vulnerable --port 87872) Inspect Available Vectors
bash
agentprey vectors list --category prompt-injection3) Initialize Project Config + Auth Commands
bash
agentprey initagentprey auth activate --key <KEY>agentprey auth statusagentprey auth refreshagentprey vectors sync --pro4) Run the HTTP Scanner
bash
agentprey scan --target http://127.0.0.1:8787/chat --category prompt-injection5) Run an OpenClaw Local-Path Scan
bash
agentprey scan --type openclaw --target ./path/to/openclaw-project6) Use TUI Mode
bash
agentprey scan --target http://127.0.0.1:8787/chat --category prompt-injection --ui tui7) Run From Config Defaults
bash
agentprey scan --config .agentprey.toml8) Generate Output Artifacts
bash
agentprey scan --target http://127.0.0.1:8787/chat --category prompt-injection --json-out ./scan.jsonbash
agentprey scan --target http://127.0.0.1:8787/chat --category prompt-injection --html-out ./scan.html9) Upload And Share
bash
agentprey auth activate --key <KEY>agentprey vectors sync --proagentprey scan --type openclaw --target ./path/to/openclaw-project --uploadUpload runs after the local scan completes. If the backend is configured with APP_BASE_URL, the CLI prints a share URL that resolves to /reports/<share_id>.
10) Tune Resilience Controls
bash
agentprey scan --target http://127.0.0.1:8787/chat --category prompt-injection --retries 2 --retry-backoff-ms 250 --max-concurrent 2 --rate-limit-rps 1011) Try a Resistant Target
bash
python3 scripts/mock_agent.py --mode resistant --port 8787agentprey scan --target http://127.0.0.1:8787/chat --category prompt-injectionCalibration Sanity Check
Vulnerable mode should trigger findings. Resistant mode should stay near-zero false positives.
bash
# vulnerable baselinepython3 scripts/mock_agent.py --mode vulnerable --port 8787agentprey scan --target http://127.0.0.1:8787/chat --category prompt-injection# resistant baselinepython3 scripts/mock_agent.py --mode resistant --port 8787agentprey scan --target http://127.0.0.1:8787/chat --category prompt-injectionPro Activation
- Checkout from
/pricing. - Get your activation key from checkout success or email backup.
- Activate with
agentprey auth activate --key <KEY>. - Sync Pro vectors with
agentprey vectors sync --pro. - Run a Pro scan with the entitled vector bundle.
bash
agentprey auth activate --key <KEY>agentprey vectors sync --proagentprey scan --type openclaw --target ./path/to/openclaw-project --uploadTroubleshooting
auth failed
Re-activate with the latest key, then refresh and verify local auth status.
bash
agentprey auth activate --key <KEY>agentprey auth refreshagentprey auth statusno vectors found
Verify the vectors directory and sync Pro vectors if you are on the Pro tier.
bash
agentprey vectors list --vectors-dir vectorsagentprey vectors sync --proconnection refused
Start or fix the target service, then rerun scan against the correct endpoint.
bash
python3 scripts/mock_agent.py --mode vulnerable --port 8787agentprey scan --target http://127.0.0.1:8787/chat --category prompt-injection --html-out ./scan.htmlKey Recovery
- Visit agentprey.com/recover.
- Enter your checkout email.
- If the email matches an account, AgentPrey will attempt to send a replacement key.
bash
agentprey auth activate --key <NEW_KEY>agentprey vectors sync --pro