Skills/ClawHub/varg-birthday-video

varg-birthday-video@1.0.2

CAUTION

Publisher claims: "Turns a name, an age and a few photos into a personalized AI birthday video on varg: a song that sings their name, their photo coming to life as they blow out the candles, a "then and now" montage, an epic trailer starring them, a pet's birthday, an animated e-card or invitation. Asks the 5 questions that make it theirs, makes the stills first (GPT Image 2.5 spells the name on the cake), animates them (Wan 3, Seedance 2.5), makes the song (ElevenLabs Music sings the name), then exports one file that plays on WhatsApp and iMessage. Use when someone asks for a birthday video, a happy birthday message, a birthday song with a name, a birthday surprise, a video for a friend's, partner's, mom's or dad's birthday, a milestone birthday (18, 30, 50, 80), a pet's birthday or a birthday invitation. Not for weddings, anniversaries and holiday greetings (use varg-occasion-video) or a business sending birthday videos to every customer (make-personalized-videos-at-scale on varg how to)." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher vargai · joined 9 days agoInstalls 120Last detonated 2 h ago
What would fix thisWatchDispute verdict

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-06 and scored it 61/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: HTML comment carrying imperative instructions to the agent. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

CRITICAL
HTML comment carrying imperative instructions to the agentREADME.md:1 · HTML comment carrying imperative instructions to the agentFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01

No other findings across 573 lines in 7 files.

Cost to the agent

Instructions loaded
≈2,242 tok
1 file · 7 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

19 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim vargai: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
  3. New publisher≈ +3 on the totalTime clears this on its own after 14 and 30 days. Claiming the handle (+50) is the fastest way past it.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim vargaiPropose a patch to the maintainer