ClawHub
Back to skill

Security audit

Cron Doctor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward cron-diagnosis guide, with some elevated inspection and report-writing steps users should approve before running.

Install this if you want an agent to help inspect cron failures. Before use, tell the agent whether it may run privileged inspection commands or write the report file, and review reports carefully if your cron jobs contain secrets, internal paths, or business-sensitive automation details.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest advertises very broad trigger phrases such as 'job health check', 'scheduled task errors', and 'backup failed', which can cause the skill to activate on common operational requests beyond narrowly scoped cron diagnosis. Over-broad routing increases the chance an agent invokes this skill in unrelated contexts and then follows its file/system inspection and reporting steps without the user explicitly requesting those actions.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
85% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 29)May include surrounding context.

bash
# List user's crontab
crontab -l

# List system crontabs
sudo cat /etc/crontab

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
91% confidence
Finding

The skill recommends using 'sudo cat /etc/crontab' to inspect system crontabs, which encourages privileged execution. In an agent setting, prompting for or using elevated privileges expands blast radius and may expose sensitive system-wide scheduled tasks and secrets embedded in job definitions.

Content

Scanner excerpt · SKILL.md (reported line 32)May include surrounding context.

crontab -l

List system crontabs

sudo cat /etc/crontab ls -la /etc/cron.d/

text

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs writing a report file to ~/workspace/reports/cron-health-YYYY-MM-DD.md as part of normal operation, but gives no warning that it will modify local state or create files. In agent contexts, silent filesystem writes are risky because they may overwrite existing reports, leak sensitive operational details into predictable locations, or violate user expectations for read-only diagnostics.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.