Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 70% confidence
- Finding
- Without declared permissions the skill's intent is opaque and cannot be validated.
WeryAI video tool — subtitle erase
Security checks across malware telemetry and agentic risk
Overview
The artifacts describe ClawHub and Convex maintainer/development workflows with sensitive but disclosed actions that fit their stated purposes.
Install only if you want ClawHub/Convex maintainer automation. Review the autoreview helper before use because it defaults to full-access nested Codex review, and use the moderation and publishing workflows only with the intended authenticated accounts and explicit targets.
SkillSpector
By NVIDIA
Vulnerability Patterns
- MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)
VirusTotal
62/62 vendors flagged this skill as clean.