The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external documentation files to generate development tasks and has access to tools like Write and Bash. Maliciously crafted content within these input documents could attempt to influence the agent's task generation or tool usage.
Ingestion points: The skill reads data from docs/devdocs/01-requirements.md, docs/devdocs/02-system-design.md, and docs/devdocs/03-test-cases.md (specified in SKILL.md).
Boundary markers: There are no explicit instructions for the agent to use specific delimiters or ignore embedded instructions when reading these external documents.
Capability inventory: The skill utilizes Read, Write, Glob, Grep, AskUserQuestion, TodoWrite, and Bash tools.
Sanitization: No specific sanitization, filtering, or escaping of the ingested document content is defined in the instructions.

dev-tasks