Skills/ClawHub/ontology-agent

ontology-agent@1.0.0

VERIFIED

Publisher claims: "Ontology Agent — a self-contained, vendor-neutral, portable skill that turns any company description into a runnable business "ontology": a knowledge graph (semantic layer) + logic graph (logic layer) + decision graph (decision layer) + an AI expert team. As the company grows it can connect to real people and IM (DingTalk / WeCom / Feishu). Use it when you want to digitize a company, build an AI-employee team, model an enterprise as agents, or turn a one-person company / e-commerce / small business into a runnable agent system. Trigger words: ontology, enterprise digital twin, AI employees, expert team, one-person-company setup, enterprise knowledge graph, Ontology Agent, turn my company into agents. China-optimized edition (24 departments, 8 industry packs, DingTalk/WeCom/Feishu connectors). For enterprise-grade deployment (custom build / edge-cloud sync / air-gapped Palantir-style mode) contact Weishu AI." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher ontoai · joined 10 days agoInstalls 286Last detonated 2 h ago
$clawhub install ontology-agent
WatchReport an issue

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-11-06 and scored it 87/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. 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
Unicode escape sequence detectedscripts/init.py:528 · Unicode escape sequence detected — may contain obfuscated payloadsFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
Unicode escape sequence detectedscripts/init.py:530 · Unicode escape sequence detected — may contain obfuscated payloadsFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
Unicode escape sequence detectedscripts/init.py:529 · Unicode escape sequence detected — may contain obfuscated payloadsFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
LOW
Prompt injection attemptreferences/action_specs.yaml:918 · Prompt injection attempt — model control tokens · informational: not an instruction fileFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01

Cost to the agent

Instructions loaded
≈6,391 tok
1 file · 85 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.