Skills/ClawHub/openclaw-marshal

openclaw-marshal@1.0.2

CAUTION· install only

Publisher claims: "Compliance and policy enforcement for agent workspaces. Define security policies, audit compliance, check command restrictions, and generate audit-ready reports. Free alert layer — upgrade to openclaw-marshal-pro for active enforcement, blocking, and automated remediation." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher atlaspa · publishing for 280 daysInstalls 2,641Last detonated 3 h 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 2026-11-19 and scored it 70/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Destructive command against a filesystem root or device; Destructive command against a filesystem root or device; Pipe-to-shell pattern. 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 2: marshal.py: error: the following arguments are required: command
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

CRITICAL
Destructive command against a filesystem root or devicescripts/marshal.py:736 · Destructive command against a filesystem root or devicereturn "Use targeted paths instead of 'rm -rf /'. Scope deletion to specific directories."Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Destructive command against a filesystem root or devicescripts/marshal.py:182 · Destructive command against a filesystem root or device"curl|bash", "wget -O-|sh", "rm -rf /", "chmod 777",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Pipe-to-shell patternscripts/marshal.py:119 · Pipe-to-shell pattern — downloads and immediately executes remote code"block": ["curl|bash", "wget -O-|sh", "rm -rf /", "chmod 777"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
CRITICAL
Destructive command against a filesystem root or devicescripts/marshal.py:119 · Destructive command against a filesystem root or device"block": ["curl|bash", "wget -O-|sh", "rm -rf /", "chmod 777"],Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive file system command detectedscripts/marshal.py:215 · Destructive file system command detected"block": ["curl|bash", "wget -O-|sh", "rm -rf /", "chmod 777"],Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Pipe-to-shell patternscripts/marshal.py:153 · Pipe-to-shell pattern — downloads and immediately executes remote code"block": ["curl|bash", "wget -O-|sh", "rm -rf /", "chmod 777"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
HIGH
Destructive file system command detectedscripts/marshal.py:736 · Destructive file system command detectedreturn "Use targeted paths instead of 'rm -rf /'. Scope deletion to specific directories."Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Pipe-to-shell patternscripts/marshal.py:215 · Pipe-to-shell pattern — downloads and immediately executes remote code"block": ["curl|bash", "wget -O-|sh", "rm -rf /", "chmod 777"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
HIGH
Destructive file system command detectedSKILL.md:87 · Destructive file system command detected| **Command Safety** | Dangerous patterns (eval, exec, pipe-to-shell, rm -rf /) | CRITICAL |Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive file system command detectedscripts/marshal.py:182 · Destructive file system command detected"curl|bash", "wget -O-|sh", "rm -rf /", "chmod 777",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathsscripts/marshal.py:586 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesrequired = [".env", "*.pem", "*.key"]Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
CRITICAL
Destructive command against a filesystem root or devicescripts/marshal.py:153 · Destructive command against a filesystem root or device"block": ["curl|bash", "wget -O-|sh", "rm -rf /", "chmod 777"],Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Destructive command against a filesystem root or devicescripts/marshal.py:215 · Destructive command against a filesystem root or device"block": ["curl|bash", "wget -O-|sh", "rm -rf /", "chmod 777"],Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive file system command detectedscripts/marshal.py:153 · Destructive file system command detected"block": ["curl|bash", "wget -O-|sh", "rm -rf /", "chmod 777"],Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Pipe-to-shell patternscripts/marshal.py:182 · Pipe-to-shell pattern — downloads and immediately executes remote code"curl|bash", "wget -O-|sh", "rm -rf /", "chmod 777",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
HIGH
Destructive file system command detectedscripts/marshal.py:119 · Destructive file system command detected"block": ["curl|bash", "wget -O-|sh", "rm -rf /", "chmod 777"],Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python exec or eval of computed codescripts/marshal.py:739 · Python exec or eval of computed codeif "eval() call" in desc or "exec() call" in desc:Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
File permission modification commandscripts/marshal.py:738 · File permission modification command — agent changes file ownership/permissionsreturn "Use restrictive permissions (e.g., chmod 755 or chmod 644)."Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandscripts/marshal.py:119 · File permission modification command — agent changes file ownership/permissions"block": ["curl|bash", "wget -O-|sh", "rm -rf /", "chmod 777"],Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandscripts/marshal.py:215 · File permission modification command — agent changes file ownership/permissions"block": ["curl|bash", "wget -O-|sh", "rm -rf /", "chmod 777"],Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Remote installer piped to shellscripts/marshal.py:119 · Remote installer piped to shell"block": ["curl|bash", "wget -O-|sh", "rm -rf /", "chmod 777"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Remote installer piped to shellscripts/marshal.py:153 · Remote installer piped to shell"block": ["curl|bash", "wget -O-|sh", "rm -rf /", "chmod 777"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Python subprocess execution detectedscripts/marshal.py:746 · Python subprocess execution detectedreturn "Use subprocess.run() with a list of arguments (no shell=True)."Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Remote installer piped to shellscripts/marshal.py:215 · Remote installer piped to shell"block": ["curl|bash", "wget -O-|sh", "rm -rf /", "chmod 777"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Remote installer piped to shellscripts/marshal.py:182 · Remote installer piped to shell"curl|bash", "wget -O-|sh", "rm -rf /", "chmod 777",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
File permission modification commandscripts/marshal.py:153 · File permission modification command — agent changes file ownership/permissions"block": ["curl|bash", "wget -O-|sh", "rm -rf /", "chmod 777"],Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandscripts/marshal.py:182 · File permission modification command — agent changes file ownership/permissions"curl|bash", "wget -O-|sh", "rm -rf /", "chmod 777",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Python exec or eval of computed codescripts/marshal.py:78 · Python exec or eval of computed code(re.compile(r"\beval\b\s*\("), "eval() call"),Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
HIGH
Access to sensitive file pathsscripts/marshal.py:770 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesreturn "Create a .gitignore with patterns for .env, *.pem, and *.key."Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python exec or eval of computed codescripts/marshal.py:1468 · Python exec or eval of computed code"chmod 777", "eval(", "pickle.load",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
Python exec or eval of computed codescripts/marshal.py:79 · Python exec or eval of computed code(re.compile(r"\bexec\b\s*\("), "exec() call"),Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05

Cost to the agent

Instructions loaded
≈989 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

10 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Destructive command against a filesystem root or device≈ +9 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  2. Pipe-to-shell pattern≈ +9 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  3. Unclaimed publisher≈ +8 on the totalClaim atlaspa: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  4. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  5. 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.
  6. Python exec or eval of computed code≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim atlaspaPropose a patch to the maintainer