The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon data from external specifications and issue tracker tickets to manage a complex task graph.
Ingestion points: Untrusted data enters the agent context through the reading of the specification and the issue tracker tickets (SKILL.md, Step 1 and 4).
Boundary markers: The instructions do not define clear boundaries or provide 'ignore embedded instructions' warnings when processing the content of the tickets.
Capability inventory: The skill utilizes powerful tools including bash and file system operations (read, edit, write), as well as the ability to spawn subagents to execute these tools.
Sanitization: There is no evidence of sanitization or validation of the content found within the tickets before it is passed to implementer subagents.

implement-spec