Back to plugin

Security audit

code-crawler

Security checks for vulnerabilities and agentic risk

Overview

The completed scan reported no findings, supporting a benign verdict with medium confidence, though the scan alone cannot guarantee the plugin is risk-free.

The scan supports a benign assessment, but its evidence is limited to one completed scanner reporting no findings. Consider whether the plugin’s requested access fits your needs before installing; the run context does not identify it as a trusted OpenClaw plugin.

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 was not run because this plugin release contains no bundled skills.

Endor dependency reachability

Checked Nov 21, 2026 · 1:42 PM UTC

Not analyzed: Endor report-only scanning is not enabled for this plugin.