The Agent Skills Directory

[DYNAMIC_CONTEXT_INJECTION]: The skill executes a shell command at load time using the ! syntax to resolve configuration settings via a local helper script (yaml-helper.sh). The execution is limited to a script within the project's directory structure and uses hardcoded arguments.
[INDIRECT_PROMPT_INJECTION]: The skill ingests content from various local markdown files and interpolates it into the generated QA plan, creating a potential surface for indirect prompt injection.
Ingestion points: Reads from story files in production/epics/, sprint plans in production/sprints/, and design documents in design/gdd/.
Boundary markers: No specific delimiters or instructions to ignore embedded commands are used when placing external content into the generated markdown tables and sections.
Capability inventory: The skill possesses Write and Edit capabilities for local files, and restricted Bash access for configuration resolution.
Sanitization: There is no evidence of sanitization or escaping of the ingested markdown content before it is interpolated into the final output.

qa-plan