Back to skill

Security audit

Kling AI

Security checks for vulnerabilities and agentic risk

Overview

ClawScan classified this skill as benign because its reported purpose and environment fit appear reasonable, while noting overly broad activation terms; confidence is medium and the scan was partial.

The verdict is benign, but it does not mean risk-free. Consider whether broad activation on ordinary words is acceptable to you. Skillspector completed only partial analysis (15.4% coverage), and some checks could not fully evaluate obfuscated text or script contents, so the scan does not establish that all components are safe.

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
  • 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)

L004 activates the skill on generic terms such as "balance", "character", "subject", "element", and "series" without requiring Kling or media-generation context.

Medium
Category
Trigger Abuse
Confidence
98% confidence
Finding

The description explicitly says to use the skill whenever the user mentions any listed term. Several terms occur routinely in unrelated requests, such as account balances, literary characters, or mathematical series, and the activation instruction does not exclude those contexts.

Content

No source excerpt is available for this finding.