Skills/ClawHub/openclaw-daily-ops

openclaw-daily-ops@1.0.0

CAUTION· static only

Publisher claims: "Daily cost reporting + session hygiene for OpenClaw deployments. Tracks per-session API spend, shows 7-day trend, and wipes zombie sessions >24h old to preve..." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher zylcold · publishing for 244 daysInstalls 1,108Last detonated 1 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 2026-11-16 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: Context shift attempt; Prompt injection; Authorization escalation language. 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

CRITICAL
Context shift attemptSKILL.md:53 · Context shift attempt — trying to change operational mode1. Enable Developer Mode in Discord (Settings → Advanced → Developer Mode)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File type combined with upload actionSKILL.md:115 · File type combined with upload action — agent may exfiltrate local data filesExecute `scripts/cost_report.py --config /path/to/config.json` and capture output.Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionSKILL.md:170 · File type combined with upload action — agent may exfiltrate local data filesYes. Run the setup on each machine with its own `config.json`. Both can post to the same Discord webhook.Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
CRITICAL
Prompt injectionSKILL.md:53 · Prompt injection — known jailbreak technique reference1. Enable Developer Mode in Discord (Settings → Advanced → Developer Mode)Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Authorization escalation languageSKILL.md:53 · Authorization escalation language1. Enable Developer Mode in Discord (Settings → Advanced → Developer Mode)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Process kill commandSKILL.md:8 · Process kill command — agent can terminate processesTwo tasks in one nightly cron: **know what you spent, kill what's dead.**Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Discord webhook URLconfig.example.json:4 · Discord webhook URL — data will be sent to Discord"discord_webhook": "https://discord.com/api/webhooks/YOUR_WEBHOOK_ID/YOUR_WEBHOOK_TOKEN",Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Discord webhook URLSKILL.md:35 · Discord webhook URL — data will be sent to Discord"discord_webhook": "https://discord.com/api/webhooks/YOUR/WEBHOOK",Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionSKILL.md:118 · File type combined with upload action — agent may exfiltrate local data filesExecute `scripts/zombie_killer.py --config /path/to/config.json` and capture output.Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈1,347 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

19 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim zylcold: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Discord webhook URL≈ +4 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
  3. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
  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 zylcoldPropose a patch to the maintainer