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 agentmods add skills/adversa-ai/secureclaw/skillnpx skills add adversa-ai/secureclaw --skill skillgit clone --depth 1 https://github.com/adversa-ai/secureclawWhat 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 | $0.00095 | $0.01495 |
| Opus 5 | $0.00048 | $0.00747 |
| Sonnet 5 | $0.00019 | $0.00299 |
| Haiku 4.5 | $0.00010 | $0.00150 |
Grade B, and why
secureclaw scanned grade B with 3 findings 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 3d 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.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
eval/exec, chmod 777, credential access, mass email/message sends, Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
2. Before executing destructive or sensitive commands (rm -rf, curl|sh, Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
2. Before executing destructive or sensitive commands (rm -rf, curl|sh, The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
16 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- checksums.json 1.5 KB
- configs/dangerous-commands.json 1.5 KB
- configs/injection-patterns.json 2.4 KB
- configs/privacy-rules.json 2.1 KB
- configs/supply-chain-ioc.json 1.0 KB
- README.md 2.8 KB
- scripts/check-advisories.sh 1.4 KB runs code
- scripts/check-integrity.sh 2.8 KB runs code
- scripts/check-privacy.sh 2.9 KB runs code
- scripts/emergency-response.sh 3.0 KB runs code
- scripts/install.sh 4.7 KB runs code
- scripts/quick-audit.sh 11 KB runs code
- scripts/quick-harden.sh 5.2 KB runs code
- scripts/scan-skills.sh 3.0 KB runs code
- scripts/uninstall.sh 2.2 KB runs code
- skill.json 4.4 KB
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.
- 3d ago First seen · 125 lines · 95 tokens per session scan B 616f9d5ae63c
secureclaw is a skill published in the GitHub repository adversa-ai/secureclaw (347 stars, last pushed 4mo ago), with no licence file. It adds 95 tokens to every session and 1,495 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 3 findings (asks for root, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
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.
security-guide
OpenClaw 安全部署指南 / Security deployment guide — help users secure their OpenClaw installation.
dependency-auditor
Audit npm, pip, and Go dependencies that OpenClaw skills try to install. Checks for known vulnerabilities, typosquatting, and malicious packages.
network-watcher
Audit and monitor network requests made by OpenClaw skills. Detects data exfiltration, unauthorized API calls, and suspicious outbound connections.
config-hardener
Audit and harden your OpenClaw configuration. Checks AGENTS.md, gateway settings, sandbox config, and permission policies for security weaknesses.