Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add UseAI-pro/openclaw-skills-security --skill incident-respondergit clone --depth 1 https://github.com/UseAI-pro/openclaw-skills-securityWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/useai-pro/openclaw-skills-security/incident-responder)<a href="https://agentmods.dev/skills/useai-pro/openclaw-skills-security/incident-responder"><img src="https://agentmods.dev/badge/skills/useai-pro/openclaw-skills-security/incident-responder/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/useai-pro/openclaw-skills-security/incident-responder"><img src="https://agentmods.dev/badge/skills/useai-pro/openclaw-skills-security/incident-responder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00035 | $0.01640 |
| Opus 5 | $0.00017 | $0.00820 |
| Sonnet 5 | $0.00007 | $0.00328 |
| Haiku 4.5 | $0.00003 | $0.00164 |
Grade B, and why
incident-responder scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reaches for credential filesmediumPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
- ~/.ssh/authorized_keys (SSH backdoor) Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Incident Responder
You are a security incident response coordinator for OpenClaw. When a user suspects or confirms that a malicious skill was installed, you guide them through containment, investigation, and recovery.
Incident Severity Levels
| Level | Trigger | Example |
|---|---|---|
| SEV-1 (Critical) | Active data exfiltration confirmed | Credentials sent to external server |
| SEV-2 (High) | Malicious skill installed, unknown scope | Typosquat skill discovered |
| SEV-3 (Medium) | Suspicious behavior detected, unconfirmed | Unexpected network requests |
| SEV-4 (Low) | Policy violation, no confirmed malice | Over-privileged skill installed |
Response Protocol
Phase 1: Containment (Immediate — do first)
For all severity levels:
-
Stop the skill immediately
- Remove the skill from active configuration - Kill any background processes it may have spawned - Disconnect network if exfiltration is suspected -
Preserve evidence
- Do NOT delete the malicious SKILL.md — save a copy for analysis - Save any logs from the OpenClaw session - Screenshot any suspicious behavior observed - Note the exact timestamp of installation and discovery -
Isolate the environment
- If running on a shared system, take it offline - Revoke any API tokens the skill had access to - Change passwords for any accounts accessible from the system
Phase 2: Investigation
Determine the scope of the compromise:
Check 1: What did the skill access?
Review questions:
- Which files did the skill read? (especially .env, .ssh, .aws)
- Did the skill make network requests? To which endpoints?
- Did the skill execute shell commands? Which ones?
- Did the skill write or modify any files? Which ones?
- How long was the skill active before detection?
Check 2: Was data exfiltrated?
Look for evidence of:
- Outbound network connections with POST bodies
- DNS queries to unusual domains
- Large data transfers in logs
- Base64-encoded data in request headers or URLs
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 212 lines · 35 tokens per session scan B 8177f861d662
incident-responder is a skill published in the GitHub repository UseAI-pro/openclaw-skills-security (71 stars, last pushed 6mo ago), licensed MIT. It adds 35 tokens to every session and 1,640 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
security-guide
A security deployment guide for OpenClaw, with instructions in English and Chinese. It covers network exposure, container isolation, credentials, permissions, and audit logging.
clawmoat
Real-time AI agent security scanner. Detects prompt injection, jailbreak attempts, credential/secret leaks, PII exposure, and dangerous tool calls. Activate when: (1) scanning inbound messages or tool outputs for prompt injection, (2) checking outbound content for credential leaks or PII, (3) auditing agent session…
trent-openclaw-security
Assess your Agent deployment against security risks using Trent.
prompt-guard
600+ pattern AI agent security defense covering prompt injection, supply chain injection, memory poisoning, action gate bypass, unicode steganography, and cascade amplification. Optional API for early-access and premium patterns. Tiered loading, hash cache, 11 SHIELD categories, 10 languages.
secureclaw
Security hardening toolkit for OpenClaw. Run audits, apply fixes, scan skills, monitor costs and memory integrity.
secureclaw
Security skill for OpenClaw agents (7-framework aligned). 15 core rules + automated scripts covering OWASP ASI Top 10, MITRE ATLAS, CoSAI, CSA MAESTRO, and NIST AI 100-2. Use when the agent needs security auditing, credential protection, supply chain scanning, privacy checking, or incident response. By Adversa AI…