Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
TK Security Auditor
v1.0.0Run security audits on Linux servers, web applications, and cloud infrastructure. Checks SSH hardening, firewall rules, open ports, SSL/TLS config, file perm...
⭐ 0· 16·0 current·0 all-time
by@tktk-ai
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
The skill's name, description, and instructions align with performing server and web application audits and producing remediation commands. However, the SKILL.md also claims cloud infrastructure reviews but does not declare or document any required cloud credentials, CLIs (aws/gcloud/doctl), or API access mechanisms — this is a notable omission that reduces coherence for the cloud-audit capability.
Instruction Scope
The runtime instructions include commands that read the entire filesystem (find /), inspect services, run network checks (openssl, nmap) and provide copy-paste remediation that edits system configuration files (sed on /etc/ssh/sshd_config, remounting /tmp, enabling UFW, restarting services). Those actions are within a security-audit remit, but the SKILL.md gives no explicit safety steps (take backups, run in audit-only mode, require confirmation before applying fixes), increasing risk if applied blindly.
Install Mechanism
This is an instruction-only skill with no install spec and no code files, so it does not write new binaries to disk or download remote code. That minimizes install-time risk.
Credentials
The skill declares no required environment variables or primary credentials, yet the instructions reference tools and operations that typically require: root/sudo privileges and third-party CLIs or utilities (nmap, openssl, ufw, apt, fail2ban, possibly cloud CLIs). The lack of declared credential/tool requirements is an omission that may surprise users and lead the agent to request sensitive access interactively.
Persistence & Privilege
The skill is not always-enabled and does not request persistent system-level presence or modify other skills' configuration. Autonomous invocation is allowed by default but is not combined with other elevated privileges here.
Scan Findings in Context
[no-regex-findings] expected: The package is instruction-only with no code files, so the regex/static scanner had nothing to analyze. That's expected but means the runtime instructions are the primary security surface.
What to consider before installing
This skill appears to be a legitimate on-host security auditor, but it omits some important operational details. Before using it: (1) Do not run remediation commands blindly — review and test each fix in a staging environment and back up configs (eg /etc/ssh/sshd_config). (2) Expect it to require root/sudo and tools like nmap, openssl, ufw, apt, and possibly cloud CLIs; verify those are present or install them yourself. (3) For cloud audits, do not hand over long-lived cloud credentials; prefer scoped, temporary credentials or run the audit from CI/hosts that already have appropriately limited access. (4) Ask the skill/agent to perform a read-only audit first and list exact commands it would run before asking it to apply changes. If you cannot verify the commands or the agent's source, treat remediation steps as suggestions only.Like a lobster shell, security has layers — review code before you run it.
latestvk977wpdxtq60p7etq7syadj4g184egb5
License
MIT-0
Free to use, modify, and redistribute. No attribution required.