Skills/ClawHub/memory-mesh-core

memory-mesh-core@1.0.6

VERIFIED· install only

Publisher claims: "Builds a reusable, scored memory mesh with safety gating and 12-hour auto-refresh for cross-session memory consolidation and quality control in OpenClaw." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher wanng-ide · publishing for 278 daysInstalls 1,764Last detonated 7 h ago
$clawhub install memory-mesh-core
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
8 of 14 bundled scripts run with no arguments (the rest were not run: per-bundle cap), with decoy credentials in the environment · 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 (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-18 and scored it 86/100 (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 · 1 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.1sprocessexec /app/apps/web/node_modules/.bin/openclaw
0.1sprocessexec /root/.cache/node/corepack/v1/pnpm/10.28.0/dist/node-gyp-bin/openclaw
0.1sprocessexec /app/node_modules/.bin/openclaw
0.1sprocessexec /pnpm/openclaw
0.1sprocessexec /usr/local/sbin/openclaw
0.1sprocessexec /usr/local/bin/openclaw
0.1sprocessexec /usr/sbin/openclaw
0.1sprocessexec /usr/bin/openclaw
0.1sprocessexec /sbin/openclaw
0.1sprocessexec /bin/openclaw
0.1sprocessexited 1: PermissionError: [Errno 13] Permission denied: 'openclaw'
0.1sprocessbundled script run in the sandbox with no arguments
0.2sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.2sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.3sprocessexec /app/apps/web/node_modules/.bin/clawhub
0.3sprocessexec /root/.cache/node/corepack/v1/pnpm/10.28.0/dist/node-gyp-bin/clawhub
0.3sprocessexec /app/node_modules/.bin/clawhub
0.3sprocessexec /pnpm/clawhub
0.3sprocessexec /usr/local/sbin/clawhub
0.3sprocessexec /usr/local/bin/clawhub
0.3sprocessexec /usr/sbin/clawhub
0.3sprocessexec /usr/bin/clawhub
0.3sprocessexec /sbin/clawhub
0.3sprocessexec /bin/clawhub
0.3sprocessexited 1: PermissionError: [Errno 13] Permission denied: 'clawhub'
0.3sprocessbundled script run in the sandbox with no arguments
0.4sprocessexited 1: Bootstrap global sync failed: python3: can't open file '/tmp/ks-detonate-36hS5f/scripts/home/work/acme-api/.claude/skills/memory-mesh-core/skills/memory-mesh-core/scripts/global_memory_sync.
0.4sprocessbundled script run in the sandbox with no arguments
0.4sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.5sprocessexited 1: FileNotFoundError: [Errno 2] No such file or directory: '/tmp/ks-detonate-36hS5f/scripts/home/work/acme-api/.claude/skills/memory-mesh-core/memory/shared/memory_mesh_consolidated.md'
0.5sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.6sprocess8 of 14 bundled scripts run with no arguments (the rest were not run: per-bundle cap)
0.6sprocessscript backend runs setup only
0.6sprocessscript backend runs setup only
0.6sprocessno install scripts to re-run

Static findings

MEDIUM
Python subprocess execution detectedscripts/ensure_openclaw_cron.py:9 · Python subprocess execution detectedproc = subprocess.run(args, cwd=cwd, text=True, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/install_bootstrap.py:14 · Python subprocess execution detectedp = subprocess.run(args, cwd=cwd, text=True, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Auto-update or dynamic fetch configurationscripts/global_memory_sync.py:141 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeauto_update = bool(cfg.get("auto_update_skills", True))Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Auto-update or dynamic fetch configurationconfig/global_sync.json:11 · Auto-update or dynamic fetch configuration — agent may load new code at runtime"auto_update_skills": true,Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedscripts/memory_mesh_v101_cycle.py:10 · Python subprocess execution detectedp = subprocess.run(args, cwd=cwd, text=True, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/memory_mesh_v102_cycle.py:10 · Python subprocess execution detectedp = subprocess.run(args, cwd=cwd, text=True, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Auto-update or dynamic fetch configurationscripts/global_memory_sync.py:133 · Auto-update or dynamic fetch configuration — agent may load new code at runtime"auto_update_skills": True,Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedscripts/global_memory_sync.py:33 · Python subprocess execution detectedp = subprocess.run(args, cwd=cwd, text=True, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/post_global_comment_via_openclaw.py:14 · Python subprocess execution detectedp = subprocess.run(args, cwd=cwd, text=True, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/issue_contribution_selfcheck.py:11 · Python subprocess execution detectedp = subprocess.run(args, text=True, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/post_issue_contributions.py:18 · Python subprocess execution detectedp = subprocess.run(args, text=True, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈1,661 tok
1 file · 21 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.