ClawHub
Back to skill

Security audit

Cron Failure Runbook

Security checks for vulnerabilities and agentic risk

Overview

This is a plain troubleshooting runbook for failed scheduled jobs, with no bundled code or hidden persistence behavior.

Install this if you want a structured runbook for failed scheduled automation. Expect the agent to inspect scheduler configuration, run the failing command manually, check whether required secrets are accessible without printing them, and possibly perform small health/API checks or reversible local fixes under the troubleshooting task.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Session Persistence

Medium
Category
Rogue Agent
Confidence
75% 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 33)May include surrounding context.

md
## Procedure

1. Identify the scheduler context.
   - Job name, plist/cron entry, command, cwd, shell, user, and expected environment.
   - Last successful run and last failed/no-op run.

2. Reproduce in the same runtime lane.

Static analysis

No suspicious patterns detected.