Skills/ClawHub/self-improving

self-improving@2.6.0

VERIFIED· install only

Publisher claims: "Self-reflect, self-critique, self-learn, and organize memory with structured logging" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher paudyyin · publishing for 156 daysInstalls 594Last detonated 15 h ago
$clawhub install self-improving
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 84/100 (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

HIGH
Hidden zero-width characters detectedSKILL.md:1 · Hidden zero-width characters detected — may conceal content---Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
HIGH
Instructs the agent to modify its persistent memory or instruction filesSKILL.md:654 · Instructs the agent to modify its persistent memory or instruction files6. **Promote aggressively** - if in doubt, add to SOUL.md or AGENTS.mdFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentmemory-template.md:9 · HTML comment carrying imperative instructions to the agentPatterns confirmed by user, never decayFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filessetup.md:110 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction fileUpdate `AGENTS.md` by complementing the existing `## Memory` section. Do not replace the whole section and do not remove existing lines.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 filessetup.md:156 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file- Reusable global rule or preference → append to `~/self-improving/memory.md`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 filessetup.md:62 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction fileAdd to your AGENTS.md or workspace config: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:274 · Instructs the agent to modify its persistent memory or instruction files- Missing automation �?add to AGENTS.mdFix: 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:88 · Instructs the agent to modify its persistent memory or instruction files**Preference signals** �?add to `memory.md` if explicit:Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈9,179 tok
1 file · 32 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.