Back to skill
Skillv1.0.0
VirusTotal security
Ai C Plan · External malware reputation and Code Insight signals for this exact artifact hash.
Scanner verdict
SuspiciousApr 30, 2026, 4:45 AM
- Hash
- 027251be19c5c22bf70e656842d9c1bb1d3a9c383cb4c261886ed4932454eedd
- Source
- palm
- Verdict
- suspicious
- Code Insight
- Type: OpenClaw Skill Name: ai-c-plan Version: 1.0.0 The skill is classified as suspicious due to instructions in `SKILL.md` that direct the AI agent to interact with the file system outside its presumed workspace using absolute paths. Specifically, it instructs the agent to read from `/home/adige/AI-C/desing` and write to `/home/adige/AI-C/progress.json`. While the skill includes a general rule 'Workspace dışına yazma' (Do not write outside the workspace), the explicit instruction to write to an absolute path creates an exception, indicating a potential prompt injection vulnerability that allows the agent to operate beyond its intended sandbox. This represents a risky capability without clear malicious intent (e.g., data exfiltration to external endpoints or installing backdoors), thus classifying it as suspicious rather than malicious.
- External report
- View on VirusTotal