The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill evaluates potentially untrusted data from project files to determine plan validity.\n
Ingestion points: The agent reads content from plan.md, spec.md, and project files such as conductor/tracks.md and the existing codebase.\n
Boundary markers: The instructions lack explicit delimiters or safety instructions to prevent the agent from following instructions embedded within the plan.md file during evaluation.\n
Capability inventory: The skill has the ability to read and write files, specifically updating the metadata.json file to manage the lifecycle of a project track.\n
Sanitization: There is no description of sanitization, filtering, or validation performed on the content of the ingested files before they are processed by the evaluation logic.

loop-plan-evaluator