Back to skill
Skillv11.2.1
VirusTotal security
CrabPath · External malware reputation and Code Insight signals for this exact artifact hash.
Scanner verdict
SuspiciousApr 30, 2026, 4:38 AM
- Hash
- acdfb56629adf8d2c39625b60517c9f423fe5b9f9de79e14919983e1bda0be8c
- Source
- palm
- Verdict
- suspicious
- Code Insight
- Type: OpenClaw Skill Name: crabpath Version: 11.2.1 The OpenClaw AgentSkills skill bundle, CrabPath, is classified as suspicious due to significant prompt injection vulnerabilities and a high-risk operational profile. The `examples/openclaw_adapter/agents_hook.md` file explicitly instructs an AI agent to execute `query_brain.py`, `learn_correction.py`, and `crabpath inject` commands with user-controlled input, creating direct prompt injection vectors against the agent's memory and decision-making. Additionally, the skill bundle exhibits extensive file system access (reading/writing state, logs, and workspace files), network communication (to OpenAI for embeddings and LLM routing), and frequent subprocess execution of its own CLI and Python scripts, including a persistent daemon. While these capabilities are integral to its stated purpose as a memory graph engine, their combination with direct user-input execution paths presents a notable security risk.
- External report
- View on VirusTotal