The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process content from an external reference file (./references/animation-system.md). This ingestion creates a surface for indirect prompt injection where malicious instructions embedded in the documentation could influence agent behavior.
Ingestion points: The agent is instructed to read ./references/animation-system.md before generating responses.
Boundary markers: Absent. The instructions do not specify any delimiters or safety warnings to ignore potentially malicious instructions within the external reference data.
Capability inventory: The skill is primarily focused on code generation and technical explanation. No high-risk capabilities such as arbitrary command execution, network exfiltration, or file system modifications were identified in the provided content.
Sanitization: Absent. There is no mention of filtering, escaping, or validating the content retrieved from the local reference file.

makepad-animation