The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to interact with the gsd-sdk for context validation and to perform repair operations on the filesystem.
[INDIRECT_PROMPT_INJECTION]: The skill analyzes the .planning/ directory, which may contain untrusted data that could influence agent behavior.
Ingestion points: Files located within the .planning/ directory as processed by SKILL.md.
Boundary markers: The skill lacks explicit markers or instructions to ignore embedded prompts in the analyzed data.
Capability inventory: The skill has access to Bash, Write, Read, and AskUserQuestion tools, allowing for substantial system changes.
Sanitization: There is no evidence of sanitization or validation of the content read from the planning directory.

gsd-health