Back to skill

Security audit

Video Call Agent

Security checks for vulnerabilities and agentic risk

Overview

The skill fits its stated Runway video-call purpose, but it should be reviewed because it runs an unpinned npm server and handles sensitive call transcripts, recordings, and user context.

Review this skill before installing. Use it only if you trust the npm package publisher and are comfortable sending avatar images, personality prompts, call audio/video, transcripts, and recordings to Runway. Pin and review the npm runtime where possible, use a narrowly scoped Runway API key, avoid sensitive user context in persistent avatar prompts, and get clear consent before recording or transcribing calls.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (1)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:4
Finding

Unpinned npm Package May Execute Mutable Remote Code

Content
View full analysis
Remediation
View remediation
" ``` 2. Avoid implicit package downloads through an unversioned `npx` command. Install the pinned dependency first and execute the verified local binary, or use: ```bash npx --offline openclaw-video-call ``` after a trusted installation. 3. Distribute and enforce a lockfile with integrity metadata. Use `npm ci` rather than unconstrained installation so dependency resolution is reproducible. 4. Verify package provenance and signatures where supported. Ensure the reviewed source commit, published npm artifact, and documented repository correspond to one another. 5. Audit the runtime and its transitive dependencies before deployment. Add automated dependency scanning and fail installation when integrity or provenance checks do not pass. 6. Run the server with least privilege in a restricted environment: - Provide only the required environment variables. - Restrict filesystem access. - Limit outbound network destinations where practical. - Do not run the package as root or an administrative user. 7. Use a narrowly scoped Runway credential if supported, rotate it regularly, and revoke it immediately if package compromise is suspected. 8. Pin and separately review future updates instead of automatically resolving the latest registry release. ]]>
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (10)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
80% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · SKILL.md (reported line 14)May include surrounding context.

md
## Privacy & Data Handling

- **Runway API**: Only data you explicitly pass (avatar image, personality text, call audio/video) is sent to Runway ([dev.runwayml.com](https://dev.runwayml.com)). Nothing is uploaded automatically. Avatars can be deleted anytime via `DELETE /v1/avatars/{id}`.
- **Personality**: The avatar personality is built from the agent's own identity — its name, communication style, and knowledge of the user. No local files are read; the agent uses context it already has.
- **Tunnel**: The cloudflared tunnel is optional and only needed if the user answers calls from a different device. Without it, everything stays on localhost. No tunnel is created unless you explicitly install and run cloudflared.
- **npm package**: The runtime is published at [npmjs.com/package/openclaw-video-call](https://www.npmjs.com/package/openclaw-video-call). Source code: [github.com/runwayml/openclaw-skills](https://github.com/runwayml/openclaw-skills/tree/main/video-call-ai-character).

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly routes call audio/video to Runway, retrieves transcripts, and instructs the agent to download and resend recordings, but it does not require obtaining participant consent or warning about recording/transcription laws. In many jurisdictions this can create legal, privacy, and compliance exposure, especially for two-party consent environments or sensitive workplace conversations.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The skill instructs users to run an unpinned package via npx openclaw-video-call, which fetches and executes whatever version is current at invocation time. This creates a supply-chain risk: a compromised publisher account, malicious new release, or dependency hijack could lead to arbitrary code execution on the host.

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 58)May include surrounding context.

Before creating a new avatar, check if you already have one:

bash
curl http://localhost:7891/api/avatars

If the response contains an avatar, use its id and skip to "Making a Call". Only create a new avatar if the list is empty.

Ssd 3

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill encourages embedding user-specific context, preferences, projects, and timezone into the avatar 'personality' prompt and reusing it across future calls. That increases unnecessary sharing and persistence of personal/contextual data with an external service, broadening the blast radius of prompt leakage, over-collection, or misuse.

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 146)May include surrounding context.

  1. Generate one with Runway text-to-image — if none of the quick picks fit your character, or if the user specifically asks for a custom avatar look. Use the Runway API with model gemini_2.5_flash:
bash
curl -X POST https://api.dev.runwayml.com/v1/text_to_image \
  -H "Authorization: Bearer $RUNWAYML_API_SECRET" \
  -H "X-Runway-Version: 2024-11-06" \
  -H "Content-Type: application/json" \

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 146)May include surrounding context.

  1. Generate one with Runway text-to-image — if none of the quick picks fit your character, or if the user specifically asks for a custom avatar look. Use the Runway API with model gemini_2.5_flash:
bash
curl -X POST https://api.dev.runwayml.com/v1/text_to_image \
  -H "Authorization: Bearer $RUNWAYML_API_SECRET" \
  -H "X-Runway-Version: 2024-11-06" \
  -H "Content-Type: application/json" \

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 183)May include surrounding context.

  1. Generate one with Runway text-to-image — if none of the quick picks fit your character, or if the user specifically asks for a custom avatar look. Use the Runway API with model gemini_2.5_flash:
bash
curl -X POST https://api.dev.runwayml.com/v1/text_to_image \
  -H "Authorization: Bearer $RUNWAYML_API_SECRET" \
  -H "X-Runway-Version: 2024-11-06" \
  -H "Content-Type: application/json" \

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 268)May include surrounding context.

List existing avatars

bash
curl http://localhost:7891/api/avatars

Making a Call

Ssd 3

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The post-call flow directs the agent to retrieve the full transcript and recording URL, download the recording, and resend it to the user. This duplicates sensitive conversation artifacts across additional storage locations and channels, increasing the chance of accidental disclosure, oversharing, or mishandling of confidential discussions.

Content

No source excerpt is available for this finding.