Back to skill

Security audit

Kling AI

Security checks for vulnerabilities and agentic risk

Overview

The Kling integration is clearly scoped, but its setup can run an unverified downloaded installer without asking first.

Review and install a trusted CLI release yourself before using this skill, and require approval for further installation steps. Check whether its automatic installation and synchronization of other agent skills is acceptable. Kling requests pass through OOMOL, and video generation may consume credits. The complete bundled artifact was inspected, but the external installers were unavailable for review.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The supplied code installs software from an Oomol-hosted endpoint rather than performing Kling AI operations. Nothing in the chunk establishes this installation as a supporting dependency for the declared purpose. The downloaded script's contents are not provided, so its further behavior cannot be determined.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping a mutable HTTPS installer directly into bash executes its contents without integrity verification or a review step. If the distribution endpoint or release pipeline is compromised, attacker-controlled code could access local files and credentials or establish persistence; the legitimate CLI dependency and conditional setup do not eliminate that supply-chain risk.

Content

Scanner excerpt · SKILL.md (reported line 56)May include surrounding context.

The setup workflow executes downloaded installation scripts without warning about local system changes or remote-code execution.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The fallback setup directs the agent to execute downloaded shell or PowerShell code without requiring explicit approval for software installation or explaining its local effects. Restricting this step to a missing-CLI error reduces exposure, but it still crosses from operating a connector into executing external code with the agent's local privileges.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 77)May include surrounding context.

md
- **`OOMOL_INSUFFICIENT_CREDIT`** — OOMOL billing stop. Recharge at `https://console.oomol.com/billing/token-recharge` before retrying.

- **HTTP 402 without `OOMOL_INSUFFICIENT_CREDIT`** — the third-party account itself has no active plan or credit. Report the provider error message as is; do not ask the user to recharge OOMOL.

## Resources