ClawHub
Back to skill

Security audit

varg-ad-localize

Security checks for vulnerabilities and agentic risk

Overview

The scanners classify this skill as benign because its reported activity appears aligned with its stated purpose, while noting privacy and unpinned installer risks; confidence is medium and coverage is incomplete.

Before installing, decide whether you are comfortable sending scripts, voice, or identifiable footage to external services, and confirm you have authority to share it and understand the providers’ data policies. The installer and repository reference are unpinned, and Skillspector reported partial coverage, so the benign verdict is not a guarantee that every risk was assessed.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

The localization workflow lacks a privacy warning about sending user media to third-party processing services.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The advertised workflow processes scripts, voices, and talking-face footage through external services without establishing a privacy or authorization prerequisite. Naming the providers provides some transparency, but users could still submit confidential campaigns or identifiable media without understanding onward processing and retention.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
90% confidence
Finding

The command invokes an unpinned npm package through npx and installs skills from an unpinned repository reference. Although this is an installer rather than an MCP server, a compromised future package release or repository revision could introduce executable code or malicious agent instructions with the user's privileges.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 20)May include surrounding context.

md
openclaw:
    requires:
      anyBins:
        - curl
        - ffmpeg
    homepage: https://varg.ai/how-to
compatibility: >-

The workflow sends ad scripts and talking-face media to external AI services without a privacy warning.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

The operational instructions send scripts to a hosted speech endpoint and direct external processing of talking-face shots without a privacy check before transmission. The consented-clone requirement helps address voice authorization, but does not establish permission to disclose confidential scripts or identifiable footage to the processing providers.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 55)May include surrounding context.

eleven_v4 with the same voice as the source (or a consented clone of the real speaker), one call for the whole script:

bash
curl -s -X POST https://api.varg.ai/v2/speech -H "Authorization: Bearer $VARG_API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"eleven_v4","voice":"Brian","text":"<transcreated script>"}'