Ae1
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md - ✅ `SKILL.md` exists with Name and Description
Security audit
Security checks for vulnerabilities and agentic risk
This is a registry-management skill whose sensitive actions are visible and aligned with publishing and managing OpenClaw skills.
Before installing, treat this as a publishing and registry-management helper: only run publish, sync, uninstall, delete, hide, or unhide after confirming the target skill, account, and registry, and protect the local ClawHub token with appropriate filesystem permissions.
Referenced artifact was not completely inspected
- ✅ `SKILL.md` exists with Name and Description
Section headings such as "MISIÓN" and "CONFIGURACIÓN" establish a Spanish-only presentation, while the document does not state that Spanish is required or provide an opt-in or alternative language. This is a natural-language locale policy issue because the skill effectively forces a specific language without user choice or justification.
This markdown file documents deletion, hiding, unhiding, and uninstall operations, which can affect published skills and user environment state, but it does not include any cautionary warning about reversibility, permissions, or consequences. Under the markdown-file criteria for missing user warnings, user-facing documentation should warn when actions may affect data or system integrity.
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
# Full workflow automation
./publish-to-clawhub.sh validate <path> # Check structure
./publish-to-clawhub.sh package <path> # Create tarball
./publish-to-clawhub.sh publish <path> # Upload to registry
./publish-to-clawhub.sh sync <dir> # Batch publish
The file explicitly documents local paths including ~/.config/clawhub/token, revealing the location of an authentication token and the broader local skill/workspace layout. While not a secret disclosure by itself, this materially aids follow-on attacks, social engineering, or malicious local tooling by telling an attacker exactly where to look for sensitive session material.
## 📁 FILES
- `~/.openclaw/skills/clawhub/SKILL.md` (this file)
- `~/.openclaw/workspace/scripts/publish-to-clawhub.sh` (publishing automation)
- `~/.openclaw/workspace/docs/clawhub-publishing-guide.md` (documentation)
- `~/.config/clawhub/token` (authentication token)