Back to skill

Security audit

varg-consistent-characters

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marked this skill suspicious because it reports uploading identifiable people’s photos to an external service without first warning the user or confirming permission; scan coverage was partial.

Before installing, consider whether you are comfortable sending identifiable photos to Varg and its generation providers. Confirm you have permission to upload and use the people’s likenesses; the scan does not establish applicable retention or deletion controls. Coverage was incomplete: only part of the Markdown skill was inspected, and tool-misuse analysis was degraded, so the scan cannot establish that no other issues exist.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

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 22)May include surrounding context.

md
openclaw:
    requires:
      anyBins:
        - curl
        - bun
    homepage: https://varg.ai
compatibility: >-

The workflow uploads identifiable actor photos without a privacy warning or prior confirmation.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The workflow directs the agent to upload identifiable actor photos to an external service before establishing whether the user authorizes that disclosure and has permission to use the depicted people’s likenesses. External image processing is integral to the advertised task, which reduces suspicion of malicious exfiltration, but the later still-image approval does not protect photos already uploaded.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
65% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 150)May include surrounding context.

md
Key facts:

- `Image({...})` is a lazy thenable: `await` resolves it, `.file.data()` gives the bytes. Awaited results are cached, so the later video render reuses them for free.
- Run it in the background (`nohup bun run <project>-images.ts > images.log 2>&1 &`) and report the PID.
- Show the user: the cards + location + every scene. Iterate on individual scene prompts (only the changed one regenerates) until approved.

No bun? Generate the same stills one by one with `POST /v2/image` (or MCP `generate_image`), passing the references in `files`. Keep the prompts identical to the ones you will use in the render.

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 184)May include surrounding context.

md
### 3.2 Cloud TSX rules

`POST https://api.varg.ai/v2/render` with `{"code": "<tsx>"}` (MCP: `render_video` with `code`):

- **No imports, no `createVarg`**: `Render/Clip/Image/Video/Music/Captions` and `varg` are injected as globals. Local LSP errors on this file are expected and fine.
- Must `export default (<Render ...>...)`; no named exports.

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 193)May include surrounding context.

Price it first (MCP estimate_cost with tool render and the code, or POST /v2/estimate on each clip's request) and get the user's go-ahead. Then submit and poll:

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 . < template-cloud.tsx)}"
# -> {"id":"job_xxx",...}; poll every 15s:

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 197)May include surrounding context.

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

-> {"id":"job_xxx",...}; poll every 15s:

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

completed -> output.outputs[0].url (s3.varg.ai mp4)

text