ClawAudit verdict

auto-video-generator

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

Demo video recording skill using Playwright native recording with mandatory user confirmation steps before recording; the executionSinkDetected refers to documented Playwright automation scripts, no malicious behavior.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

0
security
100
transparency
90
maintenance

Findings (10)

Pattern match high

Pipe to python — executes piped content as Python code

CI_CD_DOCUMENTATION.md · prose · downgraded · | Python

Pattern match high

References sudo — requests elevated privileges

CI_CD_DOCUMENTATION.md · code · sudo

Pattern match high

apt-get install — installs system packages

CI_CD_DOCUMENTATION.md · code · apt-get install

Pattern match high

<script> tag in markdown — potential code injection

vscode-extension/src/configPanel.ts · prose · downgraded · <script

Pattern match high

HTTP request to bare IP address — common in malicious payloads

web-ui/README.md · code · http://127.0.0.1

Pattern match medium

Instructs covert action — may act without user awareness

SKILL.md · prose · downgraded · silently

Pattern match medium

Opens WebSocket connection

web-ui/README.md · code · WebSocket

Pattern match medium

References child_process — can spawn system processes

vscode-extension/src/videoGenerator.ts · prose · downgraded · child_process

Pattern match medium

Uses spawn() — can execute external programs

vscode-extension/src/videoGenerator.ts · prose · downgraded · spawn(

Pattern match low

References webhook/callback URL

CI_CD_DOCUMENTATION.md · prose · downgraded · WEBHOOK_URL

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions — minimal attack surface.

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API