The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-controlled documentation such as specifications and constitutions, which constitutes a surface for indirect prompt injection.
Ingestion points: 02-DOCS/wiki/sdd/specs/<slug>.md, 02-DOCS/wiki/sdd/constitution.md, and 02-DOCS/wiki/index.md referenced in SKILL.md.
Boundary markers: The instructions do not define explicit delimiters or instructions to ignore embedded commands within these external documents.
Capability inventory: The skill is restricted to reading and writing markdown artifacts (02-DOCS/wiki/sdd/plans/). It does not have access to shell execution, network operations, or sensitive system files.
Sanitization: No explicit validation or filtering of the ingested document content is performed before interpolation into the agent's context.
[SAFE]: The skill operates entirely within a project-local documentation workflow. It does not include any external dependencies, remote code downloads, or hardcoded secrets. Its primary function is to enforce a technical design process, and its operational scope is limited to file system writes of non-executable markdown content.

plan