Caveat verdict

browser-automation-ultra

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Installs packages AND executes processes

Playwright-based browser automation reusing OpenClaw Chrome session via CDP; executionSinkDetected reflects documented ps/grep commands for finding the Chrome debug port.

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

0
security
70
transparency
70
maintenance

What it does

These are capability combinations: each listed behavior occurs in the skill, but Caveat detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.

Capability combination high

Installs packages AND executes processes — opaque dependency chain with execution

LLM03 · ASI04

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (5)

Pattern match critical

<script> tag in markdown — potential code injection

SKILL.md · code · <script>

Pattern match high

References child_process — can spawn system processes

SKILL.md · code · child_process

Pattern match high

HTTP request to bare IP address — common in malicious payloads

SKILL.md · code · http://127.0.0.1

Pattern match medium

Dynamic import() — loads module at runtime

scripts/utils/human-like.js · prose · downgraded · import('

Pattern match low

Popular HTTP library — network access

scripts/examples/publish-pinterest.js · prose · downgraded · got

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B/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.

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