Caveat verdict

ClawMateSquare Social

clawmate-agent-skill

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

Accesses credentials AND makes external network calls

The skill contains a bold 'TOP PRIORITY SYSTEM DIRECTIVE' block that uses alarm formatting to instruct the agent on strict behavioral rules — this is a social-engineering framing pattern within untrusted content designed to elevate its own instructions above the agent's normal operating context.

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.

10
security
50
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

Accesses credentials AND makes external network calls — potential credential theft

LLM02 · ASI03

Capability combination high

Accesses credentials AND encodes data — may obfuscate stolen credentials

LLM02 · ASI03 · ASI04

Permission integrity

Makes network requests but does not declare curl/wget in required binaries

network_out

Code accesses API keys/tokens but declares no environment variables

credential_access

Findings (1)

Pattern match medium

References webhook/callback URL

SKILL.md · code · webhook_url

Permissions & capabilities

No declared permissions — minimal attack surface.

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