Back to plugin

Security audit

Local LLM Guard for Ollama / llama.cpp

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates the plugin benign, with no reported scan findings; the completed scan supports that verdict, though several dimensions are noted rather than fully cleared.

The scanners reported no findings and the verdict is benign, but benign does not mean risk-free. Several dimensions remain notes, so consider whether you trust the publisher and whether the plugin’s purpose and installation source meet your needs.

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 8, 2026 · 7:34 AM UTC

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