The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes content from external websites and YouTube transcripts, creating a surface where instructions embedded in the source material could potentially influence the AI's presentation generation.
Ingestion points: The --url and --video flags in SKILL.md define where external data enters the context.
Boundary markers: There are no explicit markers or safety instructions defined in the skill to distinguish external content from the agent's core instructions.
Capability inventory: The skill is capable of executing local shell commands via node src/cli.js and performing network requests to Felo's API infrastructure.
Sanitization: The skill does not implement specific sanitization or filtering logic for the data retrieved from external URLs.
[EXTERNAL_DOWNLOADS]: The skill instructions direct the installation of the felo-ai package and the fetching of skill files from the vendor's official GitHub repository (Felo-Inc/felo-skills). These are recognized as legitimate resources from the skill's author.
[COMMAND_EXECUTION]: The skill performs its primary tasks by executing local Node.js scripts and interacting with the system's environment variables to manage configuration.

felo-content-to-slides