The Agent Skills Directory

[SAFE]: The skill facilitates a storyboard generation workflow using provided tools. No malicious behaviors such as credential theft, remote code execution, or unauthorized network access were found. The use of image generation models is consistent with the skill's stated purpose.
[INDIRECT_PROMPT_INJECTION]: The skill demonstrates a surface for indirect prompt injection. 1. Ingestion points: User-supplied clip stories and reference images in SKILL.md Step 1. 2. Boundary markers: Absent; there are no instructions to wrap untrusted input in delimiters. 3. Capability inventory: Use of the image_generate tool. 4. Sanitization: Absent; the skill does not specify any sanitization for user-provided descriptions. This risk is considered safe as it is inherent to the creative task and mitigated by the model's safety layers.
[NO_CODE]: The skill consists of instructional text and evaluation data without including any executable scripts or binaries, reducing its attack surface.

generating-storyboards