Skills/ClawHub/self-improving-agent-pro-v1

self-improving-agent-pro-v1@1.0.0

CAUTION· static only

Publisher claims: "Universal self-improving AI agent framework. Keywords: self-improving AI agent self-correction continuous learning self-correction self-healing memory persis..." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher mark-heartflow · publishing for 196 daysInstalls 810Last detonated 17 h ago

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-19 and scored it 66/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

MEDIUM
Python subprocess execution detectedscripts/self_verify.py:32 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actionscripts/comfyui-monitor.js:225 · File type combined with upload action — agent may exfiltrate local data filesconsole.log('\n📹 Recent ComfyUI Outputs:');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionscripts/comfyui-monitor.js:263 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(` Output directory: ${OUTPUT_DIR}`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionsrc/core/three-poisons-guardrail.js:334 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`✓ Test ${i + 1}: "${tc.input.substring(0, 30)}..." → ${hasPoison ? '有毒素' : '干净'}`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandsrc/core/heartflow.py:881 · Process kill command — agent can terminate processescrisis_words = ["想死", "自杀", "不想活", "suicide", "kill myself", "end it all"]Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionbin/cli.js:104 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`Input: ${text}\n`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionscripts/generate-ppt.js:227 · File type combined with upload action — agent may exfiltrate local data files.then(() => console.log('✅ PPT 生成完成: output/HeartFlow-Presentation.pptx'))Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandsrc/core/heartflow.py:112 · Process kill command — agent can terminate processes"suicide", "kill myself", "end my life", "can't go on",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionscripts/test_v11_7.js:25 · File type combined with upload action — agent may exfiltrate local data filesconsole.log('\n=== SocialReputationEngine (已归档) ===');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionscripts/test_decision_upgrade_v11.22.js:41 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(' - Post-verification:', result.result.postVerification ? 'available' : 'N/A');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈1,800 tok
2 files · 171 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.

What would make this Verified

14 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim mark-heartflow: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  3. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
  4. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim mark-heartflowPropose a patch to the maintainer
self-improving-agent-pro-v1@1.0.0 safety verdict: Caution (static only) — KillerSkills