ClawAudit verdict

vpick-ai-video-creator

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

The skill involves an MCP link which contains an embedded authentication token. While the token's scope seems limited to generation access within VPick, it's essential to handle it with care.

⚠ 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.

100
security
100
transparency
90
maintenance

Findings (1)

Coarse signal — prose, single-step high

Instruction-prose smuggling shape detected: collects a sensitive target ("auth token") and emits it outward ("Paste"). Phrased as prose with no trigger tokens — a semantic prompt-injection / data-exfil pattern the syntactic scanners can't see. Final tier capped at Caution; review the instructions before installing.

SKILL.md · 1. **Sign up** at [vpick.10xboost.org](https://vpick.10xboost.org) (Google OAuth — new users get $1 free credit) 2. **Get your MCP link**: Go to **Settings** →

Permissions & capabilities

No declared permissions — minimal attack surface.

Is this flag fair?

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