ClawAudit verdict

raysurfer

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

The skill caches and reuses code from prior AI agent executions via Raysurfer, sending data to external hosts. While seemingly legitimate, it involves external data transmission.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

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.

60
security
50
transparency
70
maintenance

Permission integrity

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

network_out

Findings (3)

Pattern match high

Pipe to python — executes piped content as Python code

search.sh · prose · downgraded · | python3

Pattern match low

Python urllib.request — network access

search.py · prose · downgraded · urllib.request

Pattern match low

Accesses sensitive environment variables

search.ts · prose · downgraded · process.env.RAYSURFER_API_KEY

Permissions & capabilities

No declared permissions — minimal attack surface.

network_outcredential_access

Is this flag fair?

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