Caveat verdict

clawdcursor

clawd-cursor

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

Receives external input AND uses eval

Desktop GUI automation agent that binds REST API to 127.0.0.1 only, routes screenshots through the user's own configured AI provider, and clearly documents safety tiers requiring user approval for sensitive actions.

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.

5
security
70
transparency
90
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 critical

Receives external input AND uses eval — the remote code-injection pattern (data-flow not verified)

LLM01 · LLM05 · ASI01 · ASI05

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (2)

Pattern match critical

Uses eval() — can execute arbitrary code

SKILL.md · code · eval(

Pattern match high

HTTP request to bare IP address — common in malicious payloads

SKILL.md · code · http://127.0.0.1

Permissions & capabilities

No declared permissions — minimal attack surface.

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