Back to skill

Security audit

biz-analysis-narrator

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign with high confidence: scanners found no AIG issues, and the noted concerns are about installation commands whose behavior is partly outside the stated spreadsheet-analysis purpose.

The verdict is benign, but benign does not mean risk-free. Before installing, consider that the documented `npx skills` command is unpinned and that the scanner could not verify the remotely referenced skill's functionality. The reported scan covered all supported text components; the binary cover image was outside analyzer scope.

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The supplied chunk contains installation commands only. It does not read spreadsheets, calculate variances, interpret trends, or generate management narratives. Although installing dependencies can be a supporting implementation detail, these commands install the named skill itself and constitute the entire supplied behavior. The functionality of the remotely referenced skill cannot be verified from this chunk.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
88% confidence
Finding

Although this is an installation CLI rather than an MCP server, the documented command uses npx to execute an unpinned package, creating a supply-chain risk if the resolved release is compromised. Exploitation requires someone to run the installation command; the README does not itself execute anything, but execution on a finance workstation could expose sensitive business data.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
88% confidence
Finding

The release notes recommend executing an unpinned npm CLI through npx, so the code executed during installation can change independently of these release notes. This is not an MCP server reference or automatic execution, but a compromised package release could execute with the installing user's permissions.

Content

No source excerpt is available for this finding.