CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

style-sampling

Make a new episode in a proven video style - Collage Explainer, Finance Explainer, Animated Science Explainer, 3D Brand Explainer, 3D True Crime - on the person's topic. Use for "an episode of", "in the style of", "sample this style", 「用这个风格做一集」. One video to copy is reverse-any-video.

Quality

97%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Medium

Suggest reviewing before use

SKILL.md
Quality
Evals
Security
Medium

W009: Direct money access capability detected (payment gateways, crypto, banking).

What this means

The skill is specifically designed for direct financial operations, giving the agent the ability to move money or execute financial transactions — such as payment processing, cryptocurrency operations, banking integrations, or market order execution.

Why it was flagged

The skill's only payment-related route is the Pro subscription. Lines 36-37 instruct the person to run `npx hyperframes billing subscribe --feature templates --skill style-sampling`, which purchases a paid plan. Line 16 states that templates are a Pro feature and the server checks the plan. Under the service-cost exclusion, a subscription to the tool's own service could be read as ordinary service cost rather than an agent payment operation. Because the rule favours recall on ambiguous evidence, I treat the subscription as a direct purchase. Credit and media generation (line 54) are service costs with no transfer to third parties, so they are not the basis for this rating. For the direct subscription route, the control is the sign-in requirement: line 34 requires `npx hyperframes auth status` before anything else, and line 36 requires `npx hyperframes auth login` for unauthenticated users. The plan check is enforced server-side (line 16). That is a service-enforced authentication gate, so the route is classified as medium rather than high.

Report incorrect finding
Low

W011: Third-party content exposure detected (indirect prompt injection risk).

What this means

The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.

Why it was flagged

The required workflow runs web research for facts and a YouTube topic search (`references/remix.md` [34], [49]) and pulls stock footage from public sites (`references/remix.md` [47]). An outsider can publish poisoned web pages the agent must actively search for and select, but cannot force delivery into a feed the workflow monitors, so this is low.

Repository

heygen-com/hyperframes

Path

skills/style-sampling/SKILL.md

Audited
Security analysis
Snyk

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.