Caveat verdict

normieclaw-dashboard-builder

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Receives external input AND uses eval

Dashboard scaffolding skill with explicit prompt-injection defenses, mandatory RLS on all DB tables, and prohibition of hardcoded secrets; dynamic_eval is a hint but no concrete malicious eval pattern exists in the content.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

18
security
20
transparency
70
maintenance

What it does

These are capability combinations: each listed behavior occurs in the skill, but Caveat detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.

Capability combination critical

Receives external input AND uses eval — the remote code-injection pattern (data-flow not verified)

LLM01 · LLM05 · ASI01 · ASI05

Permission integrity

Code accesses API keys/tokens but declares no environment variables

credential_access

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (2)

Pattern match high

Dynamic import() — loads module at runtime

SKILL.md · code · import('

Pattern match low

Accesses sensitive environment variables

templates/middleware.ts · prose · downgraded · process.env.NEXT_PUBLIC_SUPABASE_ANON_KEY

Permissions & capabilities

No declared permissions — minimal attack surface.

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