files-memory-system
What this skill does
This skill is a memory management system for OpenClaw agents, designed to handle group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation. It provides
github/leoyeai - File System Access - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=files-memory-systemAssessments (3)
File System Access
File System Access via local-llm-review
scripts/install.sh
The script creates and writes to memory directories and files (e.g., /workspace/memory/private/GLOBAL.md, /workspace/memory/global/GLOBAL.md). This could be a risk if the skill is not properly sandboxCommand Execution
Command Execution via local-llm-review
scripts/auto-clone.sh
The script allows cloning of repositories based on user input, which could be exploited if the input is not properly sanitized. This could lead to unintended code execution or data exposure.Memory Access
Memory Access via local-llm-review
scripts/auto-load-group-memory.sh
The script loads memory files based on group ID and channel, which could be a risk if the group ID is not properly validated and the memory files contain sensitive information.Badge
Add the Anomity scan badge for files-memory-system to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of files-memory-system? Report an issue or request a rescan.
