ClawHub
Back to skill

Security audit

memory-shield

Security checks for vulnerabilities and agentic risk

Overview

This skill reads user-selected memory files to create snapshots and scan reports, with no evidence of hidden network access, deletion, or persistence.

Install only if you are comfortable giving the skill read access to the memory files or directories you choose and write access for local reports. Avoid pointing it at broad home directories or unrelated sensitive stores unless you intend those contents to be processed into masked snapshots or reports.

SkillSpector

Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill declares tools `python` and `file` and explicitly instructs running Python scripts that read memory inputs and write snapshots/reports, yet no explicit permissions model is declared. This creates a capability/authorization mismatch: an agent or platform may expose file read/write and shell-like execution without the user being clearly informed of the scope, increasing the risk of overbroad access to sensitive memory files.

Static analysis

Detected: suspicious.prompt_injection_instructions

Prompt-injection style instruction pattern detected.

Warn
Code
suspicious.prompt_injection_instructions
Location
README.md:19

Prompt-injection style instruction pattern detected.

Warn
Code
suspicious.prompt_injection_instructions
Location
SKILL.md:63