Skills/ClawHub/security-audit-openclaw

security-audit-openclaw@1.0.2

CAUTION· install only

Publisher claims: "⚠️ HIGH PRIVILEGE SECURITY AUDIT SKILL Performs comprehensive security auditing for OpenClaw deployments. Requires system-level access for legitimate securit..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher iaadoa · publishing for 249 daysInstalls 1,227Last detonated 19 min ago

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
1 of 1 bundled script run with no arguments, with decoy credentials in the environment · every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-20 and scored it 73/100 (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; Access to sensitive file paths; Privileged sudo command. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.1sprocessexited 1: PermissionError: [Errno 13] Permission denied: '/tmp/openclaw-security-reports'
0.1sprocess1 of 1 bundled script run with no arguments
0.1sprocessscript backend runs setup only
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathsSKILL.md:49 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files| Sensitive Directories | Counts file changes in /etc, ~/.ssh, etc. |Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedscripts/openclaw_security_audit.py:327 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathsscripts/openclaw_security_audit.py:106 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files'dir_changes': '目录变更: {} 个文件 (位于 /etc/ 或 ~/.ssh 等)',Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Privileged sudo commandscripts/openclaw_security_audit.py:249 · Privileged sudo command — agent may execute with elevated privileges'yellow_line_ok': 'Yellow Line Audit: sudo records={}, memory records={}',Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandscripts/openclaw_security_audit.py:127 · Privileged sudo command — agent may execute with elevated privileges'yellow_line_header': '黄线操作对比 (sudo logs vs memory)',Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandSKILL.md:54 · Privileged sudo command — agent may execute with elevated privileges| Yellow Line Audit | Compares sudo logs with memory records |Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathsscripts/openclaw_security_audit.py:226 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files'dir_changes': 'Directory Changes: {} files (in /etc/ or ~/.ssh, etc.)',Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Telegram Bot API URLscripts/openclaw_security_audit.py:981 · Telegram Bot API URL — data will be sent to Telegramurl = f"https://api.telegram.org/bot{bot_token}/sendMessage"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Says it only reads; the code writes or deletes filesscripts/openclaw_security_audit.py:350 · Says it only reads; the code writes or deletes files (stated in its description)with open(REPORT_FILE, 'w', encoding='utf-8') as f:Fix: Declare and request only the permissions the task needs.
AST02
HIGH
Privileged sudo commandscripts/openclaw_security_audit.py:247 · Privileged sudo command — agent may execute with elevated privileges'yellow_line_header': 'Yellow Line Operations Comparison (sudo logs vs memory)',Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈1,223 tok
1 file · 4 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

7 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim iaadoa: 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. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. Telegram Bot API URL≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
  5. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  6. Says it only reads; the code writes or deletes files≈ +2 on the totalDeclare and request only the permissions the task needs.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim iaadoaPropose a patch to the maintainer