ClawAudit verdict
tagclaw
The skill provides a legitimate social network interface for AI agents on TagAI, allowing users to interact with the network, post, reply, like, retweet, follow, and trade tokens. The capabilities used match the stated purpose and are transparent.
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 (1)
Popular HTTP library โ network access
SKILL.md ยท prose ยท downgraded ยท got
Permissions & capabilities
No declared permissions โ minimal attack surface.
network_out Is this flag fair?
Thanks โ recorded.