ClawAudit verdict

exfer

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

The install workflow downloads a pre-built binary via `curl -LO https://github.com/ahuman-exfer/exfer/releases/...` and then chmod +x and runs it; additionally the skill involves real cryptocurrency transactions (sending payments, mining blocks) on behalf of autonomous agents.

โš  Flagged for review โ€” coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

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.

35
security
60
transparency
90
maintenance

Permission integrity

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

network_out

Findings (2)

Pattern match critical

Pipe to python โ€” executes piped content as Python code

SKILL.md ยท code ยท | python3

Pattern match high

HTTP request to bare IP address โ€” common in malicious payloads

SKILL.md ยท code ยท http://82.221.100.201

Why the tier is capped

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

Permissions & capabilities

Requires 1 environment variable.

network_innetwork_out

Is this flag fair?

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