ClawHub
Back to skill

Security audit

Datris Memory

Security checks for vulnerabilities and agentic risk

Overview

This skill openly indexes specific local memory notes into Datris for long-term recall, with no hidden code or unrelated behavior found.

Install this only if you want Datris to index your MEMORY.md and memory/*.md notes for recall. Review those files for secrets or sensitive personal data first, and make sure you trust the configured Datris MCP server and storage account.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

High
Confidence
95% confidence
Finding
The skill description instructs invocation for very broad categories like any mention of saving, recalling, syncing, searching memory, and even generic 'memory-shaped' questions. This can cause over-triggering, making the agent route unrelated user requests into this skill and unnecessarily access or operate on long-term memory systems, increasing the chance of unintended data exposure or unwanted writes/sync actions.

Static analysis

No suspicious patterns detected.