Skills/ClawHub/agent-command-guard-hardening

agent-command-guard-hardening@1.0.0

CAUTION· install only

Publisher claims: "Harden an agent's command interception layer safely: snapshot the baseline, test a matrix of should-block, negative-control, and known-bypass cases, verify classification rather than executing destructive commands, and document the bypass surface. Use when adding or changing guards around rm, mv, chmod, sudo, launchctl, dd, or any command wrapper. Tool-agnostic; includes a matrix runner and a bypass scanner." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher cengcengcai-creator · publishing for 7 daysInstalls 0Last detonated 7d 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 2026-11-07 and scored it 79/100 (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; Privileged sudo command. 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

MEDIUM
File permission modification commandSKILL.md:53 · File permission modification command — agent changes file ownership/permissions| Negative control | proves no over-blocking | `mv --help`, `chmod --help`, `launchctl list` |Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandSKILL.md:52 · File permission modification command — agent changes file ownership/permissions| Should block | proves the guard works | `rm -rf /tmp/x`, `sudo ...`, `chmod -R 777 .` |Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Destructive file system command detectedSKILL.md:52 · Destructive file system command detected| Should block | proves the guard works | `rm -rf /tmp/x`, `sudo ...`, `chmod -R 777 .` |Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedscripts/matrix_run.py:18 · Python subprocess execution detectedp = subprocess.run(argv, capture_output=True, text=True, timeout=20)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Privileged sudo commandSKILL.md:52 · Privileged sudo command — agent may execute with elevated privileges| Should block | proves the guard works | `rm -rf /tmp/x`, `sudo ...`, `chmod -R 777 .` |Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈1,630 tok
1 file · 10 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

1 point to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim cengcengcai-creator: 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. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. New publisher≈ +3 on the totalTime clears this on its own after 14 and 30 days. Claiming the handle (+50) is the fastest way past it.
  5. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
  6. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim cengcengcai-creatorPropose a patch to the maintainer