ClawHub
Back to skill

Security audit

Dataecho Memory

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed cloud-backed memory skill, with privacy considerations but no artifact-backed malicious or deceptive behavior.

Install only if you want an agent to use DataEcho as remote persistent memory. Review what gets saved, avoid regulated or sensitive personal data, never store secrets or API keys as memories, and use forget/revoke/restore controls when memory contents or sharing tokens are no longer appropriate.

SkillSpector

Vulnerability Patterns
  • Rogue AgentSelf-Modification, Session Persistence
  • 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
Findings (3)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The instructions tell the agent to remember durable things 'at the moment you learn them' and list several subjective categories like preferences, decisions, insights, and mid-task state. Because these triggers are ambiguous and agent-decided, the skill may automatically persist user data or internal state that the user did not intend to store across sessions.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The instructions tell the agent to remember durable things 'at the moment you learn them' and list several subjective categories like preferences, decisions, insights, and mid-task state. Because these triggers are ambiguous and agent-decided, the skill may automatically persist user data or internal state that the user did not intend to store across sessions.

Session Persistence

Medium
Category
Rogue Agent
Content
One fact per file. Slug is lowercase-kebab and *says what the fact is*
(`user-prefers-tabs`, not `note-1`). Description ≤ 100 chars — it is the recall surface,
write it like a search result. Body under ~8 KB (the script warns; split bigger things).
For decisions and feedback, include **Why:** and **How to apply:** lines — a decision
without its why gets re-litigated next session. Link related memories with `[[slug]]`.
Confidence
95% confidence
Finding
This skill is explicitly designed for session persistence across sessions, machines, sandboxes, and agent platforms using a private cloud drive. While persistence is the feature, it materially increases privacy and data-retention risk because user preferences, task state, references, and decisions may be stored remotely and later recalled outside the original context; the handoff and restore features further expand exposure if memory contents include sensitive information.

Static analysis

No suspicious patterns detected.