The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests content from a local settings file, which acts as a potential surface for instructions embedded in data to influence the agent. 1. Ingestion points: Content is read from ~/.claude/gsd-core/workflows/settings.md. 2. Boundary markers: No explicit delimiters or instructions to disregard embedded commands are defined. 3. Capability inventory: The skill uses Read, Write, and Bash tools. 4. Sanitization: No evidence of input validation or sanitization is present in the skill definition.
[DYNAMIC_EXECUTION]: The skill specifies an external markdown file (~/.claude/gsd-core/workflows/settings.md) as its execution context, loading logic from a local file path at runtime.
[COMMAND_EXECUTION]: The skill is configured with Bash and Write permissions to facilitate the reading, parsing, and modification of configuration files within the user's home directory.

gsd-settings