Caveat verdict

intelligence-radar

45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.

Accesses credentials AND makes external network calls

The skill communicates with a hardcoded IP address (47.116.49.218) and caches user login credentials locally, sending them to an external server; while this appears to be an internal enterprise CRM tool, the hardcoded IP and credential transmission to an unknown third-party server warrant caution.

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.

35
security
80
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 high

Accesses credentials AND makes external network calls — potential credential theft

LLM02 · ASI03

Permission integrity

Code accesses API keys/tokens but declares no environment variables

credential_access

Findings (1)

Pattern match high

HTTP request to bare IP address — common in malicious payloads

SKILL.md · code · http://47.116.49.218

Why the tier is capped

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

Permissions & capabilities

Requires 3 system binaries. (1 elevated: curl).

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