ClawHub
Back to skill

Security audit

张掖信息化标讯搜索

Security checks for vulnerabilities and agentic risk

Overview

This skill performs a disclosed workflow to search public bidding notices and append results to a specified Excel tracker, with no evidence of hidden execution, credential use, exfiltration, or persistence.

Before installing, confirm that the Excel path is the tracker you want updated and keep a backup if the file is important. The skill appears narrowly focused on public bidding research and spreadsheet entry, but it does not instruct the agent to ask before saving new rows.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill directs the agent to modify a specific local Excel file in the user's workspace without any explicit user confirmation, dry-run option, or warning that local data will be changed. This creates a real risk of unintended file modification, duplication, corruption, or overwriting of user-maintained records, especially because the path is hardcoded and the write behavior is automatic.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.