The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and process content from local files such as docs/PLAN.md and docs/TODO.md to understand project state. This creates a potential surface for indirect prompt injection if those files contain malicious instructions, though this is inherent to the skill's purpose of context persistence.
Ingestion points: The agent reads from docs/PLAN.md, docs/TODO.md, and docs/references/ (specified in SKILL.md).
Boundary markers: The instructions do not define specific delimiters or warnings to ignore embedded instructions within these files.
Capability inventory: The skill utilizes file read and write operations to manage project documentation.
Sanitization: No explicit sanitization or validation of the file content is performed before processing.

create-project