Back to skill

Security audit

zeh-local-inspector

Security checks for vulnerabilities and agentic risk

Overview

This skill only lists the current working directory contents with a bundled read-only script, with no network, persistence, or file modification behavior observed.

Before installing, understand that the skill will reveal the current directory path and a short list of filenames from the directory where it is run. Use it only in directories you are comfortable having summarized, and prefer an updated version that respects the user's requested language.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding

The skill instructs the agent to run a local inspection script and read from the working directory, but it does not declare any explicit tool scope such as permissions or allowed-tools. That creates an authorization gap where the runtime may permit broader file access than intended, increasing the chance of unintended disclosure of local data during 'read-only' inspection.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

Line L14 states 'Return concise Chinese output,' which imposes a specific language regardless of user preference. The policy allows locale or language constraints only when the user is given a choice or the constraint is clearly justified, neither of which is present here.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.