Back to skill

Security audit

varg-character-keynote

Security checks for vulnerabilities and agentic risk

Overview

The scanners classify this skill as benign with medium confidence: findings are consistent with generating a video through Varg, while noting an unpinned installer and incomplete coverage.

Before installing, consider whether you are comfortable sending dialogue and character prompts to Varg or its generation providers, and avoid submitting sensitive content unless you have authorization. The installer version is not pinned. Coverage is incomplete because two local path-like references could not be resolved, so the benign verdict is not a guarantee of safety.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Missing privacy warning that user-provided dialogue and character prompts are sent to external generation services.

Medium
Category
Output Handling
Confidence
89% confidence
Finding

The skill describes turning the user's spoken line and character prompt into a video through a varg render. Although the README names the API and generation services, it does not explicitly warn that these user inputs leave the local environment for third-party processing.

Content

No source excerpt is available for this finding.

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

Medium
Category
MCP Rug Pull
Confidence
86% confidence
Finding

The command uses npx to execute an unpinned skills package, allowing the executable version to change between installations. A compromised package release could execute code with the installing user's permissions; however, the finding incorrectly describes this CLI installer as an MCP server.

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 21)May include surrounding context.

md
homepage: https://varg.ai
compatibility: >-
  Needs the varg MCP connection (https://mcp.varg.ai/mcp, render_video tool) or a VARG_API_KEY
  with curl for POST https://api.varg.ai/v2/render. No local dependencies.
allowed-tools: Bash(curl:*) Bash(jq:*) Read Write Edit
---

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 21)May include surrounding context.

md
homepage: https://varg.ai
compatibility: >-
  Needs the varg MCP connection (https://mcp.varg.ai/mcp, render_video tool) or a VARG_API_KEY
  with curl for POST https://api.varg.ai/v2/render. No local dependencies.
allowed-tools: Bash(curl:*) Bash(jq:*) Read Write Edit
---

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 80)May include surrounding context.

  • API: save it as keynote.tsx, then
bash
curl -s -X POST https://api.varg.ai/v2/render \
  -H "Authorization: Bearer $VARG_API_KEY" -H "Content-Type: application/json" \
  -d "{\"code\": $(jq -Rs . < keynote.tsx)}"
# -> {"id":"job_xxx",...}; poll until completed, the video is at output.outputs[0].url

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 84)May include surrounding context.

-H "Authorization: Bearer $VARG_API_KEY" -H "Content-Type: application/json"
-d "{"code": $(jq -Rs . < keynote.tsx)}"

-> {"id":"job_xxx",...}; poll until completed, the video is at output.outputs[0].url

curl -s https://api.varg.ai/v2/jobs/JOB_ID -H "Authorization: Bearer $VARG_API_KEY"

text

## Rules