Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 70% confidence
- Finding
- Without declared permissions the skill's intent is opaque and cannot be validated.
Security audit
medical-training-report
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed document-generation helper that reads user-provided training materials and produces a Word report, with no evidence of hidden collection, persistence, or network activity.
Before installing, understand that the skill will process attendee lists, scores, hospital affiliations, training photos, transcripts, and case-discussion materials you provide. Use it with files you are allowed to process, review AI-generated summaries for accuracy, and be careful when pointing it at folders because report photos from that path can be embedded.
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
65/65 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.