The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes the plannotator command to validate and annotate implementation checkpoint files created in the repository's docs/ folder.
[EXTERNAL_DOWNLOADS]: The agent is instructed to fetch the body and comments of issues from external trackers to gather the context necessary for implementation planning.
[PROMPT_INJECTION]: The skill processes untrusted external artifacts (PRDs, specs, and tracker issues), which creates a surface for indirect prompt injection.
Ingestion points: External artifacts and issue tracker content (SKILL.md).
Boundary markers: Absent. The instructions do not specify any delimiters to separate external data from system instructions.
Capability inventory: The skill can write files to the repository, perform network fetches for tracker data, and execute the plannotator CLI tool.
Sanitization: Absent. There is no evidence of sanitization or validation of the content retrieved from external sources before it is processed.

afk-to-issues