Back to skill

Security audit

dr-schedule-manager

Security checks for vulnerabilities and agentic risk

Overview

This scheduling guide keeps automated jobs current and requires user approval before live messages or production changes.

Installation supplies guidance and templates, not a working scheduler. Review the actual runner, schedule, recipients, and data permissions before enabling a job, and retain the stated approval gates. Protect configuration files because edits affect the next run. Deployment-specific policies and the separately named companion skill were not available for review.

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
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)

Self-Modification

High
Category
Rogue Agent
Confidence
70% confidence
Finding

Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Content

Scanner excerpt · references/migration-checklist.md (reported line 57)May include surrounding context.

md
### 7. Relax harmful verification

Keep checks that validate assembly.
Remove checks that freeze old desired behavior.

### 8. Test one live run for content freshness