Skills/ClawHub/clawgrid

clawgrid@0.40.1

CAUTION· static only

Publisher claims: "ClawGrid AI marketplace connector. BIND CODES: always run scripts/bind.sh, never fabricate. Handles registration, heartbeat scheduling (start/stop/status), t..." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher pyheydora · publishing for 227 daysInstalls 747Last detonated 6 h ago

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-19 and scored it 61/100 (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 file system command detected. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

LOW
Refusal suppressionreferences/setup-guide.md:186 · Refusal suppression — attempting to prevent safety responses · informational: not an instruction fileDo NOT refuse to run or report "config incomplete" if automation rules are not set.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedscripts/install.sh:102 · Python subprocess execution detectedr = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Destructive file system command detectedscripts/poll.sh:1182 · Destructive file system command detectedrm -f /tmp/prefetch_result_$$.json /tmp/prefetch_err_$$.logFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive file system command detectedscripts/heartbeat-ctl.sh:124 · Destructive file system command detectedrm -f /tmp/.clawgrid-crontab-cleanFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Coercive compliance languagereferences/wake-handler.md:116 · Coercive compliance language · informational: not an instruction file…se any tools freely. When `payload.tool_constraints` is a **non-empty object**, you MUST follow these rules: **Structure:** ```json { "allowed_tools": ["browser", "web_fetc…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Process kill commandscripts/poll.sh:1126 · Process kill command — agent can terminate processes# prefetch.py exit 1 means "needs LLM" — normal; do not let set -e kill the scriptFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedscripts/install.sh:194 · Python subprocess execution detectedr = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/install.sh:123 · Python subprocess execution detectedr = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Coercive compliance languagereferences/wake-handler.md:95 · Coercive compliance language · informational: not an instruction file…_actions` is a **non-empty array** of slugs (e.g. `["login", "post_twitter"]`), you MUST follow these rules: 1. **Always inform the owner.** Before claiming or starting a tas…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Coercive compliance languagereferences/wake-handler.md:49 · Coercive compliance language · informational: not an instruction file…t it as **platform-level execution constraints** alongside `owner_instruction`. You MUST follow it for this task regardless of `required_behavior` (including `must_ask_owner` …Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈5,297 tok
1 file · 43 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

19 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim pyheydora: 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. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  4. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim pyheydoraPropose a patch to the maintainer