The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it instructs the agent to execute an external 'implementation plan' exactly as specified without using boundary markers or sanitization.
Ingestion points: implementation plan and critical files referenced in SKILL.md.
Boundary markers: Absent.
Capability inventory: The skill uses file modification tools (ast-grep, Edit) and executes shell commands for building, linting, and testing.
Sanitization: Absent.
[COMMAND_EXECUTION]: The skill executes shell-based utilities like ast-grep and difft, and allows for the execution of arbitrary project-specific commands for building, linting, and testing as defined in the untrusted implementation plan.

proceed