Back to skill

Security audit

HeyGen

Security checks for vulnerabilities and agentic risk

Overview

The HeyGen workflow has sensible approval controls, but its setup can execute unverified downloaded code and introduce broader agent-skill changes without clear user approval.

Review setup before enabling this skill. Install a verified CLI release yourself, check or disable its automatic skill synchronization, and connect only the intended HeyGen account through OOMOL. Keep the stated approval requirements for generation, uploads, and deletions. This review does not verify the external installers or hosted connector implementation.

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
97% confidence
Finding

The declared purpose is HeyGen integration, but the supplied code executes an Oomol-hosted installer without establishing any connection to HeyGen functionality. This introduces remote code execution for an unrelated installation rather than demonstrating a supporting HeyGen implementation detail. The downloaded script's contents and further effects cannot be determined from this chunk.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
99% confidence
Finding

Piping a remotely fetched installer directly into Bash executes its current contents without version pinning, integrity verification, or review. A compromised distribution endpoint could execute arbitrary commands with the agent process's permissions; HTTPS and the legitimate CLI dependency do not eliminate this supply-chain risk.

Content

Scanner excerpt · SKILL.md (reported line 71)May include surrounding context.

First-time setup instructs execution of downloaded installation scripts without warning about the system-integrity impact.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The setup instructions direct the agent to execute downloaded shell or PowerShell code without explicit installation approval or an explanation that it can modify the local system. Restricting setup to a missing-CLI error reduces exposure, but a HeyGen request could still trigger local code execution beyond the user's requested service operation.

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 92)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