Skills/ClawHub/self-improvement-llm

self-improvement-llm@2.3.0

VERIFIED· install only

Publisher claims: "Autonomous AI memory and self-learning system that logs, extracts lessons, verifies improvements, adapts behavior, manages preferences, and generates reusabl..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher brucetangc · publishing for 108 daysInstalls 1,474Last detonated 4d ago
$clawhub install self-improvement-llm
WatchReport an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-10 and scored it 90/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

MEDIUM
Python subprocess execution detectedscripts/learn.py:1529 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Instructs the agent to modify its persistent memory or instruction filesSKILL.md:80 · Instructs the agent to modify its persistent memory or instruction files8. **When you modify any core file** (MEMORY.md, TOOLS.md, SOUL.md, AGENTS.md):Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Unicode escape sequence detectedscripts/learn.py:1128 · Unicode escape sequence detected — may contain obfuscated payloadssummary_text = stripped.lstrip("#\u2705\u274c\ud83d\udca1\ud83d\udccc\ud83e\udd16 ").strip()[:120]Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
HIGH
Instructs the agent to modify its persistent memory or instruction filesSKILL.md:71 · Instructs the agent to modify its persistent memory or instruction filesedit(path="MEMORY.md", oldText="从 read 结果中复制的精确文本", newText="新内容")Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Instructs the agent to modify its persistent memory or instruction filesSKILL.md:415 · Instructs the agent to modify its persistent memory or instruction files| Add principle to MEMORY.md | ✅ Auto-apply | "Simple before powerful" |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filesreferences/reflection_frameworks.md:249 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file"Fix: Update AGENTS.md workflow section to prefer parallel execution for independent subtasks."Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filesscripts/learn.py:1537 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction fileprint(f" ✅ MEMORY.md is current, nothing to add")Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Instructs the agent to modify its persistent memory or instruction filesSKILL.md:66 · Instructs the agent to modify its persistent memory or instruction filesedit(path="MEMORY.md", oldText="我印象中的内容", newText="新内容")Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filesscripts/dream.py:278 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction fileprint(f"\n📋 Would add to MEMORY.md:\n")Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Instructs the agent to modify its persistent memory or instruction filesSKILL.md:418 · Instructs the agent to modify its persistent memory or instruction files| Add rule to AGENTS.md | ⚠️ Propose | "Spawn sub-agents for long tasks" |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈4,589 tok
1 file · 12 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.