The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute specific CLI tools, canon and orchestra, to record decisions, create design artifacts, and validate workflow states. These tools are expected to be available on the system PATH and are used to manage a local SQLite database and project configuration.- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which creates a surface for indirect prompt injection attacks.
Ingestion points: According to SKILL.md, the agent reads active specifications, reviews, phase details, constraints, assessments, and project code during the research and design steps.
Boundary markers: The instructions do not define any delimiters or provide guidance to the agent to ignore instructions embedded within the files it reads.
Capability inventory: The skill has the capability to write records to a persistent local store and perform workflow operations through the canon and orchestra commands.
Sanitization: There is no mention of sanitizing, escaping, or validating the content of external files before the agent processes them.

design