Security audit

Uplo Knowledge Management

Security checks for vulnerabilities and agentic risk

Overview

The skill is for legitimate knowledge-management search, but it enables broad organizational export and runs an unpinned npm MCP server with an API token.

Install only if you trust UPLO and the npm MCP package source, can use a narrowly scoped UPLO token, and are comfortable with the agent accessing sensitive organizational knowledge. Prefer pinning the MCP server version, protecting and rotating the API key, and requiring explicit approval before any full organizational context export.

A.I.G

Vulnerability Patterns

Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
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

Findings (2)

T08 · Insecure Dependencies

Warning

Location: skill.json:28
Finding: Unpinned npm Package Is Automatically Downloaded and Executed
Content: View full analysis
Remediation: View remediation

T05 · Unauthorized Access and Privilege Escalation

Warning

Location: SKILL.md:65
Finding: Full Organizational Context Export Is Enabled Beyond Routine Search Requirements
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
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
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (3)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The listed 'When to Use' examples are extremely broad and overlap with many ordinary organizational requests, which can cause the skill to be invoked for high-sensitivity knowledge discovery without clear scoping, authorization, or least-privilege guidance. In this KM context, the danger is elevated because the skill explicitly targets expertise directories, retention strategy, tool adoption metrics, and records disposition information that may expose sensitive internal structure and governance data.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill recommends using export_org_context as a 'best friend' and says the full organizational context export reveals the state of institutional knowledge, but it provides no warning, gating, or minimization guidance for what is likely a highly sensitive bulk-export capability. In a knowledge management skill, this is especially dangerous because aggregated exports can expose expertise maps, knowledge gaps, operational dependencies, and restricted strategic documents at a scale far beyond what is needed for most user tasks.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 77% confidence
Finding: This markdown file instructs users to set an API_KEY environment variable for the MCP server, which is a sensitive credential. The README does not include any warning about protecting the key, avoiding accidental disclosure, or understanding that the skill will use authenticated access to organizational data.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.