The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill directs the agent to fetch and interpret documentation from an external source, creating an ingestion surface for potentially malicious instructions.
Ingestion points: The agent is instructed in SKILL.md to fetch documentation index from https://pixijs.download/release/docs/llms.txt and subsequent linked markdown files.
Boundary markers: There are no specific delimiters or instructions for the agent to ignore commands within the fetched documentation.
Capability inventory: The skill assumes the agent has network access to fetch these files and will process the content within its reasoning context.
Sanitization: No content filtering or validation is specified for the external documentation content.

pixijs-2d