Back to skill

Security audit

Dgcu Library AI Librarian

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because it may activate on unrelated messages containing a single book-related character, while the scan evidence is partial.

Review the skill's trigger and decide whether you are comfortable with possible activation on unrelated messages. The scanner reports guidance to limit transmitted text to the necessary query and avoid sensitive information. Treat the assessment as incomplete: two local references could not be resolved, and runtime permission enforcement is unknown.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: network.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

The keyword-only trigger includes “书” (book), causing activation for messages unrelated to library searches.

Medium
Category
Trigger Abuse
Confidence
98% confidence
Finding

The trigger explicitly accepts the single character “书” independently of library-search intent, so unrelated messages containing words such as “证书” can activate the skill. This can cause unintended routing and, if activation proceeds to a query, unnecessary transmission of message-derived text to the remote service or its model provider. The fixed endpoint, task-scope language, and explicit prohibition on sending sensitive information substantially limit the risk.

Content

No source excerpt is available for this finding.