The Agent Skills Directory

[Command Execution] (SAFE): The skill uses ls in SKILL.md to search for existing ADR directories. This is a legitimate file discovery action for documentation tasks.
[Indirect Prompt Injection] (LOW): The skill is designed to ingest and process untrusted requirement documents (PRDs/TRDs).
Ingestion points: SKILL.md Phase 0, Step 1 involves reading user-provided documentation files.
Boundary markers: Absent; no specific delimiters or safety instructions are used to distinguish document content from system instructions.
Capability inventory: SKILL.md includes directory listing (ls) and file creation/writing (Phase 5).
Sanitization: Absent; the skill lacks explicit validation or sanitization of the content extracted from requirement documents.

generating-adrs