ClawAudit verdict
create-token
nadfun-token-creation
The skill guides the user through a 4-step process for creating a token on Nad.fun, using network_out capability, which aligns with its stated purpose.
โ 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.
Permission integrity
network_out
Findings (3)
fetch() โ outbound network request
SKILL.md ยท code
Makes HTTP request to external URL
SKILL.md ยท code ยท fetch("https://
Contains shortened/invite URL
SKILL.md ยท code ยท t.me/mytoken
Permissions & capabilities
No declared permissions โ minimal attack surface.
network_out Is this flag fair?
Thanks โ recorded.