Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Auto Improve
v1.0.0Self-improvement loop that reads learnings, errors, and memory — detects patterns — and updates skills/protocols automatically. Use when the agent should get...
⭐ 0· 42·0 current·0 all-time
byKairoKid@dodge1218
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
high confidencePurpose & Capability
The name/description (self-improvement loop) lines up with the SKILL.md: it reads learnings/memory and proposes/applies changes to skills/protocols. However, the skill declares no required config paths or credentials while the instructions assume access to repository/agent files (e.g., .learnings/*, SOUL.md, AGENTS.md, skill 'Learned' sections). The absent declaration of which files it will read/write is a mismatch.
Instruction Scope
The runtime instructions explicitly tell the agent to read local learnings/memory files and to update/modify 'Skill Learned' sections, SOUL.md, AGENTS.md, memory facts, and reminder/ticket files. They allow applying changes automatically (low-risk directly, medium-risk apply+notify) with vague risk definitions and no approval workflow, file path restrictions, or human-in-the-loop gating — giving the agent broad discretion to change other skills and agent behavior.
Install Mechanism
Instruction-only skill with no install spec and no code files; nothing is written to disk by an installer. This is the lowest install risk.
Credentials
The skill requests no environment variables or declared config paths but expects access to sensitive internal files and skill artifacts. Requiring write access to other skills' files or agent configuration is a high-privilege action that should be declared and justified; the lack of declared paths/permissions is disproportionate.
Persistence & Privilege
always is false, but the skill is invocable and model-invocation is enabled, so the agent could autonomously run it. The instructions direct modification of other skills and agent-level files (AGENTS.md, SOUL.md), which counts as modifying other skills' configurations or system-wide settings — this is a privileged action that should be restricted and audited.
What to consider before installing
This skill gives an agent broad authority to read and modify other skills, memory, and agent configuration files without specifying which paths or requiring human approval. Before installing or enabling: 1) Require an explicit, narrow list of readable/writable paths and declare them in the skill metadata; 2) Add mandatory human approval for any non-reversible or non-trivial changes (no automatic 'apply' for anything beyond a very small, well-defined set); 3) Use a dry-run mode that generates proposed changes but does not write files, and require explicit user acceptance to apply; 4) Run the skill first in a sandboxed environment with backups of all agent/skill files; 5) Add detailed risk definitions and logging/audit trails for every change; 6) If you do not have strong controls and review processes, do not grant this skill permission to run autonomously or to write to other skills' files. Additional info that would change this assessment: a declared list of file paths the skill may access, explicit safety/approval gates, or code that implements a secure apply/approval workflow.Like a lobster shell, security has layers — review code before you run it.
agent-intelligencevk971hnj32500xva82zq0ecz5x584gmmhlatestvk971hnj32500xva82zq0ecz5x584gmmhself-improvementvk971hnj32500xva82zq0ecz5x584gmmh
License
MIT-0
Free to use, modify, and redistribute. No attribution required.