ClawHub
Back to skill

Security audit

OC Evolver Restart Loop Fix

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow operational repair guide for an Evolver service restart loop, with disclosed service-state changes but no hidden code or deceptive behavior.

Install only if you manage the affected Evolver service. Before using it, confirm the service can be restarted, take normal backup or rollback precautions for the lock-guard patch, and avoid running it during active workloads unless an operator has approved the disruption.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

This markdown skill describes operational steps that modify service state, including clearing a lock and restarting the service. While the Safety section says changes should be minimal and reversible, it does not explicitly warn users about potential disruption, downtime, or the effect on running services and system state.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.