The Agent Skills Directory

[PROMPT_INJECTION]: The skill identifies and updates aggregate boundaries within project instruction files (e.g., AGENTS.md, CLAUDE.md), which serves as a potential vector for indirect prompt injection. Ingestion points: Reads existing boundary definitions from AGENTS.md and CLAUDE.md. Boundary markers: No specific delimiters or safety warnings are used to isolate ingested data. Capability inventory: Possesses the capability to read from and append content to local project documentation files. Sanitization: Lacks explicit sanitization or validation of the data retrieved from external project files.

aggregate-boundaries