The Agent Skills Directory

[PROMPT_INJECTION]: Potential for indirect prompt injection as the skill reads and processes untrusted data from project files. * Ingestion points: The skill reads Java, Go, Vue, TSX, Python, and Markdown files during project-wide and single-file scans (SKILL.md). * Boundary markers: Absent. No delimiters or instructions are provided to the agent to treat file content as data rather than instructions. * Capability inventory: The skill has the capability to read files and suggests or performs code refactors and fixes based on analysis. * Sanitization: Absent. There is no validation or filtering of content ingested from external source files.

size-check