Security audit

Uplo Government

Security checks for vulnerabilities and agentic risk

Overview

This government knowledge skill is coherent, but it combines sensitive agency-context export, API-token use, and unpinned runtime package execution that users should review carefully.

Install only in a controlled environment. Pin and review the MCP server package before use, run it with minimal filesystem and network access, use a least-privilege UPLO token, and restrict full organizational exports to authorized users with appropriate classification handling and review.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally

Findings (1)

T08 · Insecure Dependencies

Warning

Location: skill.json:26
Finding: Unpinned npm Package Is Automatically Downloaded and Executed
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (3)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 86% confidence
Finding: The README advertises an export_org_context tool as a "Full organizational context snapshot" without any warning about access controls, least-privilege expectations, or the sensitivity of the exported data. In a government knowledge-management context, organizational context may include internal relationships, directives, owners, and restricted information, so normalizing broad export functionality without caution can encourage unsafe deployment and overbroad access.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The skill explicitly promotes exporting the complete agency knowledge map, including mission, structure, personnel, systems, goals, and active directives, but does not provide a strong user-facing warning, scoping requirement, or minimization guidance. In a government environment, that breadth can expose sensitive internal organizational, operational, or pre-decisional information and materially increase the risk of over-disclosure even if the user is otherwise authorized.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: This manifest defines a secret API token and injects it into the MCP process environment and HTTP configuration, but the description does not warn users that credentials will be used and transmitted to an external service endpoint. For manifest files, this falls under missing user warnings because the skill handles sensitive credentials and network communication without visible disclosure in the skill description.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.