Skills/ClawHub/ground-control

ground-control@0.3.6

CAUTION· static only

Publisher claims: "Verify OpenClaw after upgrades against an operator-maintained model, cron, and channel ground truth. Use for report-only config integrity, provider liveness, cron integrity, session smoke tests, and channel checks; require explicit approval before applying repairs." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher jonathanjing · publishing for 103 daysInstalls 1,381Last detonated 5d ago
What would fix thisWatchDispute verdict

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 2026-11-09 and scored it 63/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: HTML comment carrying imperative instructions to the agent; Instructs the agent to modify its persistent memory or instruction files. 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
Instructs the agent to modify its persistent memory or instruction filesscripts/UPGRADE_SOP.md:30 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction fileIf using an OpenClaw agent, add the sync rule to AGENTS.md:Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agenttemplates/MODEL_GROUND_TRUTH.md:4 · HTML comment carrying imperative instructions to the agentUsage: After each upgrade, run /verify against this file.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Unpinned dependencySKILL.md:49 · Unpinned dependency- After running `openclaw update` or `npm install -g openclaw@latest`Fix: Pin the exact version (`[email protected]`, `==1.2.3`) so every install gets the bytes that were reviewed.
AST06
LOW
Instructs the agent to modify its persistent memory or instruction filesREADME.md:92 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file### 2. Add the sync rule to AGENTS.mdFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filesREADME.md:94 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction fileAdd this block to your `AGENTS.md` so the agent reminds you to update ground truth when config changes:Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Instructs the agent to modify its persistent memory or instruction filesSKILL.md:58 · Instructs the agent to modify its persistent memory or instruction files4. Add the GROUND_TRUTH sync rule to your AGENTS.md (see README)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈727 tok
1 file · 7 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

17 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim jonathanjing: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
  3. Unpinned dependencies≈ +1 on the totalPin exact versions (and ideally hashes) in package.json, requirements or the install script so the bundle cannot change under you.
  4. Unpinned dependency≈ +1 on the totalPin the exact version (`[email protected]`, `==1.2.3`) so every install gets the bytes that were reviewed.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim jonathanjingPropose a patch to the maintainer