The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill defines a workflow that requires analyzing the existing codebase and calling external agents for research. This pattern ingests untrusted data from the codebase into the agent context.\n- Ingestion points: SKILL.md mandates codebase analysis through grep commands and the fuse-ai-pilot:explore-codebase agent to analyze architecture.\n- Boundary markers: Absent; the skill does not provide delimiters or instructions to ignore embedded instructions within the code being analyzed.\n- Capability inventory: The skill is documentation-centric and does not include scripts with subprocess, file-write, or network capabilities.\n- Sanitization: Absent; no sanitization of codebase content is performed before processing.

solid-rust