Back to skill

Security audit

weekly-report-pack

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with high confidence; scanners found unpinned package installation instructions and a mismatch between the stated report-writing purpose and the reported installation behavior, but no malicious behavior was identified.

Before installing, consider that the scanners report installation of an external package rather than demonstrated report generation. The unpinned `npx skills` commands may resolve to a changing version; review and pin the installer and package version if you proceed. Skillspector marked coverage complete for its declared scope, but static analysis did not inspect the binary cover image.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The observable behavior is external skill installation, not the declared report-generation workflow. Although installation could support a larger reporting implementation, no such implementation or delegation to report generation is shown. The external package's name alone does not establish that its behavior matches the description.

Content

No source excerpt is available for this finding.

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

Medium
Category
MCP Rug Pull
Confidence
89% confidence
Finding

The installation command uses npx skills without a version, allowing installation-time execution of whichever package version resolves at that time. A compromised release could execute with the installer's permissions; this is a conditional supply-chain risk, not evidence of malicious behavior or an MCP server.

Content

No source excerpt is available for this finding.

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

Medium
Category
MCP Rug Pull
Confidence
89% confidence
Finding

This installation example invokes an unversioned npm CLI through npx, so following it can execute a package release that changes independently of these release notes. A compromised release could run with the installer's permissions, although the command is ordinary installation guidance rather than an MCP server reference.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'NPX aT'.

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.