Install
$ agentstack add skill-liuweitao-shodan-skill-shodan-skill ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Shodan Skill
Use shodan-skill as the single implementation on every supported agent platform.
Run the workflow
- Confirm the command is installed with
shodan-skill --help. If it is missing, direct the user to install this package before attempting an API operation. - Use
SHODAN_API_KEYor the official Shodan CLI configuration for authentication. Never request that a key be pasted into a command, prompt, source file, or log. - Identify whether the request is read-only, credit-consuming, state-changing, destructive, or Enterprise-only. Consult [API coverage](references/api-coverage.yaml) for the exact method, path, access class, credit impact, and collected contract test. Use the [official API snapshot](references/official-api-snapshot.yaml) when checking whether the inventory matches the last retrieved documentation.
- Translate the request to the grouped kebab-case CLI. Prefer
shodan-skill GROUP ACTION --helpwhen parameters are uncertain. - Route API-plan, usage-limit, quota, remaining-credit, credit-balance, query-credit, and scan-credit requests to
shodan-skill account api-info. Useshodan-skill account profileonly for membership and profile metadata. Never treat the profile response's genericcreditsfield as the query- or scan-credit balance. - Treat an explicit user request as the instruction to execute that operation, including credits, mutations, downloads, scans, monitoring, streams, and Enterprise operations. Do not ask for a second confirmation or authorization acknowledgement.
- Use the default
directsafety mode. The CLI emits deterministic previews for applicable operations and continues immediately. Use--dry-runonly when the user asks to preview without execution. Usestrictmode only when the user explicitly requests it. - Validate every target and dynamic path segment locally, and do not add operations or expand targets beyond what the user requested. Treat Streaming and Enterprise entitlements as account requirements.
- Parse stdout as the stable JSON envelope, JSON Lines for default streams, or SSE
data:events when--stream-format sseis selected. Treat stderr as diagnostics and preserve nonzero exit codes. Never expose redacted values, signed URLs, authorization headers, cookies, or API keys. - Report skipped live verification honestly. Keep repository live-test gates separate from normal CLI execution; do not interpret a configured test environment as a request to run live tests.
Choose the focused reference
- Read [search and host](references/search-and-host.md) for host intelligence, search, count, pagination, facets, filters, tokens, and saved queries.
- Read [DNS and tools](references/dns-and-tools.md) for DNS, account, ports, protocols, public IP, HTTP headers, and official data-field references.
- Read [scans and alerts](references/scan-and-alerts.md) for scans, alerts, triggers, notifiers, and their request forms.
- Read [streaming](references/streaming.md) for feeds, JSONL/SSE, limits, idle timeouts, and reconnects.
- Read [Trends and Exploits](references/trends-and-exploits.md) for the separate Trends and Exploits services.
- Read [Enterprise](references/enterprise.md) for datasets, verified downloads, organizations, and entitlement boundaries.
- Read [official data schemas](references/data-schemas.md) for banner, exploit, and Threatnet event shapes.
- Read the [official SDK baseline](references/sdk-baseline.md) and [SDK-only operations](references/sdk-only.md) only for compatibility or API-coverage questions.
- Read [safety](references/safety.md) before any credit-consuming, state-changing, destructive, scanning, monitoring, or download operation.
Use deprecated underscore aliases only to preserve an existing workflow. Generate new instructions and examples with the grouped interface.
OpenClaw installation
Install the shodan-skill Python package first, then place this generated directory at ~/.openclaw/skills/shodan-skill. Confirm discovery with shodan-skill --help before an API request.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: liuweitao
- Source: liuweitao/shodan-skill
- License: MIT
- Homepage: https://liuweitao.github.io/shodan-skill/
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.