The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input such as the deck topic, audience description, and specific content points to generate a presentation plan and image generation prompts. This represents an attack surface for indirect prompt injection where a user might attempt to manipulate the agent's output or planning logic.
Ingestion points: User-supplied brief containing topic, audience, tone, and specific data/visual requirements (SKILL.md).
Boundary markers: The workflow does not explicitly mention the use of delimiters or instructions for the model to ignore potential commands embedded within the user-provided data.
Capability inventory: The skill is restricted to using the image_gen tool and writing plan and image files to the local presentations/ directory. It lacks network access or high-privilege system capabilities.
Sanitization: The skill lacks explicit sanitization or filtering logic for the strings extracted from the user's initial brief.

presentation-design