ClawAudit verdict

a0x-agents

45
๐ŸŸ  Risky
Significant concerns โ€” only install if you understand the risks

Accesses agent memory/notes AND makes external network calls

The skill transparently discloses wallet addresses and project URLs are sent to the a0x server; sending crypto wallet addresses plus agent knowledge to a third-party Google Cloud Run endpoint is unusual scope for a collective-brain tool.

Automated static analysis โ€” not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

0
security
40
transparency
70
maintenance

What it does

These are capability combinations: each listed behavior occurs in the skill, but ClawAudit detects co-occurrence โ€” it does not verify that one flows into another. Read the code to confirm a live chain.

Capability combination critical

Accesses agent memory/notes AND makes external network calls โ€” may leak personal data

LLM02 ยท LLM07 ยท ASI03 ยท ASI06

Capability combination high

Accesses credentials AND makes external network calls โ€” potential credential theft

LLM02 ยท ASI03

Capability combination high

Accesses agent memory AND makes external network calls โ€” may leak conversation history

LLM02 ยท LLM07 ยท ASI06

Permission integrity

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

network_out

Accesses agent memory/configuration files

agent_memory

Findings (2)

Pattern match high

Possible prompt injection โ€” attempts to redefine agent identity

SKILL.md ยท code ยท you are now

Pattern match medium

Popular HTTP library โ€” network access

SKILL.md ยท code ยท got

Permissions & capabilities

Requires 1 environment variable. (1 sensitive: A0X_MCP_API_KEY).

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