Skills/ClawHub/linux-security-guardian

linux-security-guardian@1.6.0

CAUTION· static only

Publisher claims: "Autonomous multi-client Linux server security management via SSH MCP. Runs full audit at 1 AM IST nightly via cron. Iterates over all clients and their serve..." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher cyber-bye · publishing for 202 daysInstalls 1,458Last detonated 3d ago
What would fix thisWatchDispute verdict

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-11 and scored it 66/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Authorization escalation language; Cipher/encoding reference. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

HIGH
Access to sensitive file pathsSKILL.md:178 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files| `02-users` | Accounts, root access, sudo, empty passwords, inactive | `ssh_exec(op="run", sessionId, command="cat /etc/passwd; cat /etc/shadow; ...")` |Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commandhooks/pre-action.md:40 · File permission modification command — agent changes file ownership/permissions- `chmod 1777 /tmp` — /tmp permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Authorization escalation languageSKILL.md:178 · Authorization escalation language| `02-users` | Accounts, root access, sudo, empty passwords, inactive | `ssh_exec(op="run", sessionId, command="cat /etc/passwd; cat /etc/shadow; ...")` |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File permission modification commandSKILL.md:155 · File permission modification command — agent changes file ownership/permissions| World-writable /tmp | medium | AUTO-FIX chmod |Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Cipher/encoding referenceaudit/modules/03-ssh.md:113 · Cipher/encoding reference — may contain obfuscated instructions[HIGH] 03-ssh: weak_cipher | cipher: 3des-cbc | in use: yes | action_id: ACT-YYYYMMDD-XXXFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01
HIGH
Access to sensitive file pathshooks/post-action.md:14 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files→ For account lock: grep <user> /etc/shadow | cut -d: -f2 | grep "^!"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Authorization escalation languageaudit/modules/24-swap-encryption.md:7 · Authorization escalation language · informational: not an instruction file- If swap is unencrypted, an attacker with physical or root access can read swapFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈4,075 tok
1 file · 49 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

14 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim cyber-bye: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  3. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim cyber-byePropose a patch to the maintainer