ClawAudit verdict

agentworld

aigame

45
🟠 Risky
Significant concerns — only install if you understand the risks

Accesses credentials AND makes external network calls

The game instructs the agent to send player_token credentials via HTTP (not HTTPS) to a raw IP address (111.231.112.127:9000), exposing auth tokens to interception with no domain or TLS protection.

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.

0
security
70
transparency
90
maintenance

What it does

These are capability combinations: each listed behavior occurs in the skill, but ClawAudit 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

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 (2)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · TOKEN="上一步获取的player_token

Pattern match high

HTTP request to bare IP address — common in malicious payloads

SKILL.md · code · http://111.231.112.127

Permissions & capabilities

No declared permissions — minimal attack surface.

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