HyperFrames CLI - scaffold, check frames, edit timelines, preview, render, share and project history; read JSON and recover from failures.
87%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Critical
Do not install without reviewing
Detected a prompt injection in the skill instructions. The skill contains hidden or deceptive instructions that fall outside its stated purpose and attempt to override the agent’s safety guidelines or intended behavior.
The skill's vendor reporting (a skill-start telemetry beacon, automatic post-render feedback, and "missing feature" reports that relay the user's asks to a public channel) is disclosed and serves the CLI's maintenance, but it runs without the user asking, so it is at most a sketchy-but-not-malicious pattern.
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.
The only outsider-authored content the workflow ingests is a live web page read by the optional `capture <url>` command, which the agent must actively run on a user-supplied URL, so this is low risk.
heygen-com/hyperframes
6a7b4df
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.