ClawHub
Back to skill

Security audit

Supermemory

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent for managing Supermemory, but its setup guidance endorses executing remote installer scripts directly in a shell without verification.

Review the oo CLI installation path before installing. Prefer official, version-pinned installation instructions with checksum or signature verification, and only allow write or destructive Supermemory actions after confirming the exact payload and target.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

External Script Fetching

High
Category
Supply Chain
Confidence
95% confidence
Finding

The skill instructs the agent to install software by piping a remotely fetched script directly into a shell (curl ... | bash). This is dangerous because it executes network content without verification, integrity checking, or user review; if the hosting site, transport, or distribution path is compromised, arbitrary code will run on the user's machine. In this skill context, the risk is heightened because the install command appears as an endorsed recovery step for normal operation, making it more likely an agent or user will execute it reflexively.

Content

Scanner excerpt · SKILL.md (reported line 62)May include surrounding context.

Static analysis

No suspicious patterns detected.