ClawHub
Back to skill

Security audit

memory-review

Security checks across malware telemetry and agentic risk

Overview

This skill performs a disclosed local memory-review workflow with constrained reads and writes, and I did not find hidden network, credential, destructive, or unrelated behavior.

Install this only for workspaces where the agent is allowed to review daily memory logs and update canonical memory files. Review generated decision plans and diffs before accepting changes, especially because memory files may contain sensitive operational context.

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 (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding
Without declared permissions the skill's intent is opaque and cannot be validated.

Natural-Language Policy Violations

Low
Confidence
90% confidence
Finding
The example command uses the fixed query string "主题或结论" in Chinese, with no indication that other languages are acceptable. This can be read as prescribing a specific language or locale for use, which violates the policy unless the skill offers a language choice or clearly justifies the constraint.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.dynamic_code_execution

Dynamic code execution detected.

Critical
Code
suspicious.dynamic_code_execution
Location
tests/test_memory_review.py:16