Create, import, revise, or export presentation decks through the OMA slide CLI or the ppt-master route. Use for HTML slides, editable PPTX, and PDF, PNG, or PPTX deck delivery.
85%
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
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 required workflow fetches and reads remote style definitions via `oma slide style get <slug>`, which downloads outsider-authored `design.md` files from a public GitHub repository.
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
The skill references external operational URLs (Canva MCP at https://mcp.canva.com/mcp, Canva tools documentation, and raw GitHub content for templates) for runtime setup, integration, or behavior configuration, placing it under the medium/high risk dependency tiers.
first-fluke/oh-my-agent
8a03eb1
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.