The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted workflow data from project records, creating a surface for indirect prompt injection.
Ingestion points: Data is read from the local environment and database via orchestra handoff (SKILL.md, Step 1) and canon list (SKILL.md, Steps 3 and 4).
Boundary markers: The instructions do not specify the use of delimiters or explicit 'ignore' warnings when loading data from the database into the agent's context.
Capability inventory: The skill has the capability to execute shell commands using the canon and orchestra CLI tools to create, modify, or supersede database records.
Sanitization: There is no evidence of sanitization or schema validation performed on the text content of the records before the agent processes them for routing decisions.
[COMMAND_EXECUTION]: The skill relies on executing shell commands to interact with its workflow management system.
Evidence: The skill uses canon list, canon create, canon supersede, orchestra handoff, and orchestra view to manage project state. These commands are integral to the skill's primary purpose of routing and record management.

engage