The Agent Skills Directory

Indirect Prompt Injection (LOW): The skill reads content from local markdown files into the LLM context window, which could contain adversarial instructions. * Ingestion points: qmd query, qmd search, and qmd get commands in SKILL.md. * Boundary markers: Absent; no specific delimiters or 'ignore' instructions are provided to isolate search results. * Capability inventory: Uses Bash for command execution and Read for file access. * Sanitization: Absent; the skill does not filter or sanitize retrieved file content.

qmd