The Agent Skills Directory

[SAFE]: No malicious behavior or high-risk security patterns were identified in the skill's instructions or configuration files.
[COMMAND_EXECUTION]: The skill utilizes hyperframes-cli to perform rendering, linting, and inspection of video assets, which is standard functionality for its stated purpose.
[PROMPT_INJECTION]: The skill contains an indirect prompt injection surface as it processes user-provided product details and marketing claims without explicit sanitization or boundary markers. This is a common characteristic of prompt-driven creative tools.
Ingestion points: User-supplied inputs such as product name, promise, pain words, and examples as defined in the Inputs section of SKILL.md and references/asset-contract.md.
Boundary markers: None specified in the instructions for isolating untrusted data.
Capability inventory: Use of hyperframes-cli for rendering and outputting media files to the workbench.
Sanitization: No explicit input validation or escaping mechanisms are described in the workflow.

dark-saas-magic-video