Skills/ClawHub/openclaw-emergency-rollback

openclaw-emergency-rollback@1.0.3

CAUTION· static only

Publisher claims: "OpenClaw Emergency Config Rollback — dead man's switch system for safely making risky changes to OpenClaw configuration. Use this skill whenever the user men..." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher encryptshawn · publishing for 211 daysInstalls 967Last detonated 13 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 62/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Auto-update or dynamic fetch configuration; Access to sensitive file paths. 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

MEDIUM
Process kill commandSKILL.md:46 · Process kill command — agent can terminate processesInstead, use **`kill -USR1 1`** to surgically send the reload signal directly to the root OpenClaw process.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandSKILL.md:44 · Process kill command — agent can terminate processes…ead Man's Switch, `pkill` will match the path name of the background script and kill your rescue job instantly. Instead, use **`kill -USR1 1`** to surgically send t…Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Auto-update or dynamic fetch configurationSKILL.md:49 · Auto-update or dynamic fetch configuration — agent may load new code at runtime…abotage vs Invalid JSON OpenClaw protects itself from invalid JSON by instantly hot-reloading its last known good config before the gateway even restarts. To test destructive recovery properly, you must use **Logical Sabotage**: feeding Op…Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsSKILL.md:306 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system fileslogs, workspace content files, .env, Docker/K8s environment config.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commandscripts/recovery-test.mjs:118 · Process kill command — agent can terminate processesconsole.log(` ${config.restartCommand || 'kill -USR1 1'}`);Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/restore.mjs:19 · Process kill command — agent can terminate processesconst RESTART_CMD = config.restartCommand || 'kill -USR1 1';Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈3,292 tok
1 file · 17 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

18 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim encryptshawn: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Auto-update or dynamic fetch configuration≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  3. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  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 encryptshawnPropose a patch to the maintainer