Skills/ClawHub/video-asset-sources

video-asset-sources@1.0.4

CAUTION· static only

Publisher claims: "Find B-roll, stock footage, music, sound effects, motion blocks, lower thirds, transitions, fonts, icons, logos, LUTs and HDRIs that an AI agent can really fetch and legally put in a video. A decision procedure over 97 databases, each tested on 2026-11-03: which ones answer an agent at all, which query works, which license holds, and when to generate instead. Includes 37 tested no-key queries, the traps (easy APIs you cannot use commercially, popular lists that break a license), and a credits file for every asset. Use for "find b-roll", "stock footage for this", "royalty free music", "free sound effects", "whoosh sound", "free video assets", "pexels api", "freesound", "which database should I use", "can I use this clip commercially", or whenever an edit needs a file it does not have. Not for references to study rather than use (find-references) or for the edit itself (edit-footage-with-code)." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher vargai · publishing for 215 daysInstalls 201Last detonated 30 h ago
What would fix thisWatchDispute verdict

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-13 and scored it 64/100 (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 agentGenerated by .github/readme/build.ts from SKILL.md files and .github/readme/*.json. Edit those and run `bun .github/readme/build.ts`; CI fails when this file isFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01

No other findings across 558 lines in 7 files.

Cost to the agent

Instructions loaded
≈1,908 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

16 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.
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