ClawAudit verdict

open-browser

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

Browser automation skill that delegates tasks to a local OpenBrowser agent via documented scripts; network access is inherent to browser automation and all behavior matches the stated purpose.

⚠ 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.

70
security
70
transparency
70
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (5)

Coarse signal — prose, single-step high

Instruction-prose smuggling shape detected: collects a sensitive target ("API key") and emits it outward ("Paste"). Phrased as prose with no trigger tokens — a semantic prompt-injection / data-exfil pattern the syntactic scanners can't see. Final tier capped at Caution; review the instructions before installing.

SKILL.md · | Step | Action | Where | |------|--------|-------| | 1 | Load extension | `chrome://extensions/` → Developer mode → Load unpacked → `extension/dist` | | 2 | Co

Pattern match medium

Opens WebSocket connection

references/api_reference.md · code · websocket

Pattern match medium

HTTP request to bare IP address — common in malicious payloads

references/api_reference.md · prose · downgraded · http://127.0.0.1

Pattern match low

Python urllib.request — network access

scripts/check_status.py · prose · downgraded · urllib.request

Pattern match low

Python os.environ.get — reads environment variable

scripts/check_status.py · prose · downgraded · os.environ.get(

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.

network_inpackage_install

Is this flag fair?

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