The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes project-specific data by using Glob, Grep, and Read tools to analyze the codebase and documentation. This creates a potential surface for indirect prompt injection if external or untrusted files are processed. \n- Ingestion points: The skill utilizes Read, Glob, and Grep tools to scan project files for charters, ownership claims, and evidence of capabilities as described in SKILL.md and references/evidence-and-review.md. \n- Boundary markers: No specific delimiters or boundary instructions are used to separate ingested data from agent instructions. \n- Capability inventory: The skill's capabilities are limited to information retrieval (Read, Glob, Grep) as specified in the allowed-tools frontmatter. \n- Sanitization: No explicit validation or filtering logic is implemented for the content retrieved from the file system.

strategic-clarity