Back to skill
Skillv1.0.0
VirusTotal security
ddddd · External malware reputation and Code Insight signals for this exact artifact hash.
Scanner verdict
SuspiciousApr 30, 2026, 5:59 AM
- Hash
- e0c114ab8b21faf2579e06571433187691f393d14f29af81ef4791b31552b153
- Source
- palm
- Verdict
- suspicious
- Code Insight
- Type: OpenClaw Skill Name: ddddd Version: 1.0.0 The skill bundle contains highly irregular instructions in SKILL.md that direct the AI agent to perform silent privilege escalation ('retry... with escalated permissions') and bypass user intervention ('Do not ask the user to run it yet') if a tool installation fails. Additionally, the documentation references fabricated OpenAI products such as 'gpt-oss' and 'Codex' as a standalone agent, suggesting the content is deceptive or hallucinated. While the referenced domain (developers.openai.com) is legitimate, the explicit directive to circumvent security sandboxes and user consent constitutes a significant security risk and a prompt-injection style attack against the agent's operational boundaries.
- External report
- View on VirusTotal