The Agent Skills Directory

[COMMAND_EXECUTION]: The skill facilitates the execution of local development tools, including build systems, linters, and test runners, as part of the implementation and verification workflow. Evidence: SKILL.md (Step 12) and references/checklist.md ('Suggested Checks').
[PROMPT_INJECTION]: The skill's workflow creates an attack surface for indirect prompt injection by ingesting data from external files that are then used to guide agent actions.
Ingestion points: The agent reads from KANBAN.md, member-specific profile documents, and arbitrary project source code and schemas (SKILL.md Workflow steps 1, 2, 3, 5, 6).
Boundary markers: The instructions do not define specific delimiters or isolation protocols for the content read from these external files.
Capability inventory: The skill has the ability to execute shell commands for project checks and modify files within the project's knowledge directories (SKILL.md Knowledge Updates).
Sanitization: There are no explicit instructions to sanitize or validate the content of the ingested files before they are processed by the agent.

delivery-implementation