The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes user-provided PRD documents or verbal requirements, creating an attack surface for indirect prompt injection.
Ingestion points: The skill (Step 1 in SKILL.md) reads user-specified files using the Read tool.
Boundary markers: There are no explicit delimiters or instructions to the agent to ignore embedded commands within the ingested requirement content.
Capability inventory: The skill uses the Read tool for ingestion and the Write tool to save generated test cases to the tests/ directory on the local filesystem.
Sanitization: No input validation, filtering, or sanitization of the requirement data is performed before it is processed by the agent.

test-cases