canvas-manager
Manage a Canvas through its business tools only — initialize and query projects, create Elements and Content candidates, frame Elements, wait on generation, and process design markers. Use when the user asks to create, edit, or generate anything on a Canvas, such as images, videos, storyboards, video edits, or a final composed video, or when the message contains [@design_canvas_project:...] or [@design_marker:...]. Also use when the user says 'generate an image on my canvas', 'make a video from this canvas project', 'add a new element to my design', or 'edit the marked region of this image'. Layout strategies, Connections, video point estimation, video composition, image search, asset reconciliation, and prompt inspiration live in the references.
91%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
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 uses tools like `search_canvas_image_candidates` and `search_canvas_image_prompts` which fetch external search results or prompts, representing low-risk active searching of outsider-authored content.
- Repository
dtyq/magic
- Revision
0f1432c
- Audited
- Security analysis
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.