Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 70% confidence
- Finding
- Without declared permissions the skill's intent is opaque and cannot be validated.
Related Works Report from Paper MDs
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed research workflow that reads user-selected paper files, looks up arXiv abstracts, and writes a related-works report to a chosen folder.
Use a dedicated WORKDIR and install only if you are comfortable with the skill reading the paper markdowns you provide and sending paper-title searches to Tavily while fetching metadata from arxiv.org. Avoid using it on confidential manuscripts unless that external lookup is acceptable.
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
66/66 vendors flagged this skill as clean.