The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill captures data from external URLs and incorporates it into the agent's context to generate scripts and designs, creating a risk that malicious content on a website could manipulate agent behavior.
Ingestion points: External content is read from capture/extracted/visible-text.txt and capture/extracted/asset-descriptions.md as described in references/step-1-capture.md.
Boundary markers: The instructions lack explicit boundary markers or warnings to disregard instructions embedded within the captured website data.
Capability inventory: The skill performs file system writes, spawns sub-agents, and executes shell commands via the hyperframes CLI tool across multiple steps.
Sanitization: There is no mention of sanitizing or validating the extracted text from the website before use.
[COMMAND_EXECUTION]: The skill relies on executing various CLI commands to perform its core functions, including capturing websites, generating audio, and rendering video.
Evidence: The skill instructs the agent to run commands such as npx hyperframes capture, npx hyperframes tts, npx hyperframes transcribe, npx hyperframes lint, npx hyperframes validate, npx hyperframes snapshot, and npx hyperframes render.

website-to-hyperframes