Skills/ClawHub/openclaw-rag-skill

openclaw-rag-skill@1.0.6

VERIFIED· install only

Publisher claims: "Complete RAG (Retrieval-Augmented Generation) system for OpenClaw. Indexes chat sessions, workspace code, documentation, and skills into local ChromaDB for s..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher wmantly · publishing for 280 daysInstalls 1,453Last detonated 23 min ago
$clawhub install openclaw-rag-skill
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
8 of 12 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 2026-11-21 and scored it 89/100 (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
0.1sprocessexited 2: ingest_docs.py: error: the following arguments are required: type
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
0.2sprocessexec /usr/bin/dirname
0.2sprocessexited 2: ./launch_rag_agent.sh: line 46: unexpected EOF while looking for matching `''
0.2sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.3sprocessexited 1:
0.3sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.4sprocessbundled script run in the sandbox with no arguments
0.5sprocessexited 2: rag_manage.py: error: the following arguments are required: action
0.5sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.5sprocessexited 1:
0.5sprocessbundled script run in the sandbox with no arguments
0.6sprocess8 of 12 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

HIGH
Auto-update or dynamic fetch configurationSKILL.md:355 · Auto-update or dynamic fetch configuration — agent may load new code at runtime- The auto-update script only runs local ingestion - no remote code fetchingFix: Pin versions and sources; vendor anything fetched at install time.
AST06

No other findings across 3,086 lines in 16 files.

Cost to the agent

Instructions loaded
≈2,843 tok
1 file · 16 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.