ClawHub
Back to skill

Security audit

EZ Cronjob

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed troubleshooting guide for Clawdbot cron jobs, with admin-level recovery steps that users should run carefully.

Install this only if you want your agent to help manage Clawdbot/Moltbot cron jobs. Before allowing deletion, immediate runs, Telegram delivery, log inspection, or gateway restart, verify the job ID, destination chat, and service target because those actions can remove scheduled work, send messages, reveal local log data, or briefly disrupt the gateway.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (11)

Context-Inappropriate Capability

High
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly tells agents to use exec/bash to run shell commands instead of a dedicated cron tool, which materially increases capability from scoped tool use to arbitrary command execution. Even if intended as a workaround for a deadlock, this creates a dangerous path where an agent can perform unintended system actions, especially when combined with later examples for log access and service restarts.

Content

No source excerpt is available for this finding.

Unrestricted Tool Access

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.

Content

Scanner excerpt · README.md (reported line 54)May include surrounding context.

--cron "0 9 * * 1-5"
--tz "America/New_York"
--session isolated
--message "[INSTRUCTION: DO NOT USE ANY TOOLS] Your prompt here"
--deliver --channel telegram --to "CHAT_ID"
--best-effort-deliver

text

Unrestricted Tool Access

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.

Content

Scanner excerpt · SKILL.md (reported line 37)May include surrounding context.

--cron "0 9 * * 1-5"
--tz "America/New_York"
--session isolated
--message "[INSTRUCTION: DO NOT USE ANY TOOLS] Your prompt here"
--deliver --channel telegram --to "CHAT_ID"
--best-effort-deliver

text

Unrestricted Tool Access

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.

Content

Scanner excerpt · SKILL.md (reported line 178)May include surrounding context.

--cron "0 9 * * 1-5"
--tz "America/New_York"
--session isolated
--message "[INSTRUCTION: DO NOT USE ANY TOOLS] Your prompt here"
--deliver --channel telegram --to "CHAT_ID"
--best-effort-deliver

text

Unrestricted Tool Access

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.

Content

Scanner excerpt · SKILL.md (reported line 190)May include surrounding context.

--cron "0 9 * * 1-5"
--tz "America/New_York"
--session isolated
--message "[INSTRUCTION: DO NOT USE ANY TOOLS] Your prompt here"
--deliver --channel telegram --to "CHAT_ID"
--best-effort-deliver

text

Unrestricted Tool Access

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.

Content

Scanner excerpt · SKILL.md (reported line 294)May include surrounding context.

--cron "0 9 * * 1-5"
--tz "America/New_York"
--session isolated
--message "[INSTRUCTION: DO NOT USE ANY TOOLS] Your prompt here"
--deliver --channel telegram --to "CHAT_ID"
--best-effort-deliver

text

Unrestricted Tool Access

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.

Content

Scanner excerpt · SKILL.md (reported line 316)May include surrounding context.

--cron "0 9 * * 1-5"
--tz "America/New_York"
--session isolated
--message "[INSTRUCTION: DO NOT USE ANY TOOLS] Your prompt here"
--deliver --channel telegram --to "CHAT_ID"
--best-effort-deliver

text

Unrestricted Tool Access

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.

Content

Scanner excerpt · SKILL.md (reported line 331)May include surrounding context.

--cron "0 9 * * 1-5"
--tz "America/New_York"
--session isolated
--message "[INSTRUCTION: DO NOT USE ANY TOOLS] Your prompt here"
--deliver --channel telegram --to "CHAT_ID"
--best-effort-deliver

text

Unrestricted Tool Access

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.

Content

Scanner excerpt · SKILL.md (reported line 351)May include surrounding context.

--cron "0 9 * * 1-5"
--tz "America/New_York"
--session isolated
--message "[INSTRUCTION: DO NOT USE ANY TOOLS] Your prompt here"
--deliver --channel telegram --to "CHAT_ID"
--best-effort-deliver

text

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill expands from cron troubleshooting into broader host administration by instructing agents to inspect local log files and restart the gateway service. In an agentic environment, this widens operational scope beyond the stated task and can expose sensitive system information or cause service disruption if followed automatically.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The documentation includes deleting cron jobs as a recovery step without emphasizing verification of the target job or warning about destructive consequences. In practice, an agent or operator could remove the wrong scheduled task, causing loss of business logic or missed notifications.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.