The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill establishes a workflow where the agent ingests and follows instructions from external files located in the conductor/ directory.
Ingestion points: Reads content from conductor/product.md, conductor/workflow.md, conductor/tracks.md, and track-specific plan.md files (SKILL.md).
Boundary markers: The instructions do not define clear boundary markers or safety wrappers when processing the content of these files.
Capability inventory: The skill encourages the agent to 'Respect the plan' and 'Follow workflow', effectively granting execution priority to instructions found within the project's data files.
Sanitization: There is no mention of sanitizing or validating the content of the conductor files before the agent acts upon them.

use-conductor