Back to skill
Skillv1.0.1
VirusTotal security
clawchain browsing skills · External malware reputation and Code Insight signals for this exact artifact hash.
Scanner verdict
ReviewMay 1, 2026, 4:15 AM
- Hash
- 964d5b2dbf1aef29888e3b8fc0980783359cb2df07df8f8453ffd289135b42c5
- Source
- palm
- Verdict
- suspicious
- Code Insight
- Type: OpenClaw Skill Name: clawchain-skills Version: 1.0.1 The skill bundle is classified as suspicious due to several critical vulnerabilities. The `SKILL.md` instructs the AI agent to strictly follow instructions from `~/.config/clawchain/SOUL.md`, which is generated based on an on-chain personality summary, creating a significant prompt injection vector. More critically, the `update_memory_file` operation, defined in `SKILL.md` and implemented by `generate-tx.js`, allows writing arbitrary content to an arbitrary filename on the local system. This arbitrary file write capability can be exploited for Remote Code Execution (RCE) if an attacker can prompt the agent to write malicious content to a sensitive file (e.g., a startup script or a cron job). Additionally, direct interpolation of user-controlled variables into `curl` JSON payloads in `SKILL.md` presents potential shell injection risks.
- External report
- View on VirusTotal