Back to skill
Skillv0.2.0
VirusTotal security
X Reader · External malware reputation and Code Insight signals for this exact artifact hash.
Scanner verdict
SuspiciousApr 29, 2026, 4:47 AM
- Hash
- f393dfe3466794048d3fdf2ef953cfeac32f2a1953d0c8aafe8d88736bd47b4b
- Source
- palm
- Verdict
- suspicious
- Code Insight
- Type: OpenClaw Skill Name: x-reader Version: 0.2.0 The skill is classified as suspicious due to several risky capabilities and potential vulnerabilities, despite implementing notable security safeguards. The `SKILL.md` instruction 'Local file | Read file directly' presents a prompt injection risk, potentially allowing an AI agent to be tricked into reading arbitrary local files if not properly sandboxed. Additionally, while `utils/storage.py` has strong path validation for Markdown output, the `INBOX_FILE` path (defaulting to `unified_inbox.json` or configurable via environment variable) lacks similar robust path traversal protection, potentially allowing an attacker to overwrite an arbitrary file. The skill also performs external network calls, executes `yt-dlp` via `subprocess.run`, and handles sensitive authentication sessions, though these operations are mitigated by a robust `utils/url_validator.py` for SSRF prevention, safe `subprocess.run` usage, and permission setting for session files. There is no clear evidence of intentional malicious behavior like data exfiltration or backdoor installation.
- External report
- View on VirusTotal