ClawHub
Back to skill

Security audit

agentscope-dependency-updater

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small read-only dependency-reporting helper for AgentScope projects, with no evidence of hidden modification, persistence, or data exfiltration.

Install only if you are comfortable letting it read the pyproject.toml of the project path you choose. Treat its output as a manual dependency-review aid, not as an automatic updater; it does not modify files or perform upgrades.

A.I.G

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

SkillSpector

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 (1)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding

The skill advertises executable behavior that reads project files and may generate reports, but the manifest does not declare any explicit tool scope such as permissions or allowed-tools. That mismatch weakens policy enforcement and reviewability, increasing the chance the skill is granted broader file access than intended or runs in environments where its capabilities are not properly constrained.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.