The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied prompts to generate customized editorial deck slides. This creates a vulnerability surface where malicious instructions in user data could influence the agent's output.
Ingestion points: The workflow in SKILL.md instructs the agent to replace copy in assets/template.html based on user input to create a three-slide sequence.
Boundary markers: The skill lacks specific delimiters or "ignore embedded instructions" warnings when interpolating untrusted user data into the HTML template.
Capability inventory: The skill utilizes the file_write capability to output the primary index.html artifact.
Sanitization: There are no instructions for escaping, validating, or filtering the user-provided content before it is embedded into the slide deck code.

editorial-burgundy-principles-template