ClawHub
Back to skill

Security audit

Uplo Food Safety

Security checks across malware telemetry and agentic risk

Overview

This appears to be a legitimate UPLO food-safety knowledge connector, but it needs review because it can expose broad organizational context and log sensitive compliance discussions without clear limits.

Review before installing. Use a UPLO token limited to the intended food-safety data, verify the MCP package/version you will run, and require explicit approval before using full-context export or logging conversations that mention suppliers, formulations, recalls, regulatory issues, or incident response.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The README advertises an `export_org_context` capability that can produce a full organizational context snapshot, but it provides no warning about the sensitivity of the exported data, access restrictions, or safe handling expectations. In a food safety and compliance context, such exports may include confidential HACCP plans, compliance records, traceability data, and internal quality information, which increases the risk of accidental overexposure or misuse by users integrating the skill.

Vague Triggers

Medium
Confidence
86% confidence
Finding
The skill can be invoked for broadly related food safety and compliance topics without clear trigger phrases, user-role checks, or narrow activation boundaries. In this domain, ambiguous activation increases the chance the agent will surface sensitive supplier audits, recall assessments, traceability data, or regulatory records in the wrong conversational context, especially since the skill itself encourages querying confidential documentation.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.