ClawAudit verdict
NextJS
nextjs
The skill provides expertise in building Next.js 15 apps, with no indication of malicious behavior.
⚠ 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.
Permission integrity
agent_memory
Findings (5)
Dynamic import() — loads module at runtime
deployment.md · code · import('
References agent memory files
SKILL.md · code · memory.md
Accesses sensitive environment variables
auth.md · code · process.env.AUTH_GITHUB_SECRET
References webhook/callback URL
auth.md · code · callbackUrl
Makes HTTP request to external URL
data-fetching.md · code · fetch('https://
Permissions & capabilities
No declared permissions — minimal attack surface.
agent_memory Is this flag fair?
Thanks — recorded.