The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data from the project directory and has the capability to influence the agent's next steps and task creation.
Ingestion points: Reads user stories from team-artifacts/stories/ and parent PBI files.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are used when interpolating story content into the review process.
Capability inventory: Uses TaskCreate to generate work items, writes report files to plans/reports/, and uses AskUserQuestion to guide the workflow.
Sanitization: No sanitization or validation of the input story content is performed before processing.

story-review