The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute npx remotion for rendering graphics. User-derived content is passed into the command line via the --props flag, which contains JSON-formatted data.
[COMMAND_EXECUTION]: The skill is instructed to generate new TypeScript compositions in src/infographics/compositions/ when standard templates do not suffice, which are subsequently executed during the rendering process.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) because it ingests untrusted data to construct shell commands.
Ingestion points: Input lesson markdown files, module directories, or free text as specified in SKILL.md.
Boundary markers: Absent. No delimitation or specific instructions are provided to the agent to mitigate injection risks.
Capability inventory: The skill has access to Bash, Read, Write, Edit, Grep, and Glob tools.
Sanitization: Absent. The workflow does not define methods for escaping or validating input content before it is interpolated into shell commands.
[EXTERNAL_DOWNLOADS]: The skill installation instructions involve npx skills@latest add NulightJens/jensai-skills, which fetches resources from a GitHub repository associated with the skill author.
[EXTERNAL_DOWNLOADS]: The skill utilizes external tools and libraries including npx remotion and @remotion/google-fonts for its core rendering functionality.

course-infographics