The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied topics and plans through the $ARGUMENTS variable to drive its questioning logic and codebase exploration.
Ingestion points: $ARGUMENTS in SKILL.md.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are defined for the input interpolation.
Capability inventory: The skill utilizes Bash, Read, Write, Edit, Glob, and Grep tools to explore the filesystem and generate documentation.
Sanitization: No explicit sanitization or validation of the input is specified within the instructions.
[COMMAND_EXECUTION]: The skill uses the Bash tool and references the maestro CLI for codebase searching, specification loading, and role delegation. These operations are consistent with the skill's stated purpose of codebase analysis.
[DATA_EXPOSURE]: The skill reads from the local codebase and accesses configuration files located in ~/.maestro/. This data is used internally to ground the Socratic dialogue in the reality of the existing code, and no evidence of external transmission was found.

maestro-grill