The Agent Skills Directory

[PROMPT_INJECTION]: The skill ingests untrusted data from user-provided solution context (Phase 1). Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the documentation templates. Capability inventory: Performs file system writes to the 'docs/solutions/' directory and executes 'git commit' via the shell (Phase 3). Sanitization: No sanitization or validation of external content is performed before it is interpolated into files.
[COMMAND_EXECUTION]: The skill utilizes 'git commit' to manage documentation as code. While appropriate for the task, this involves shell-based execution that handles user-influenced documentation content.

knowledge-capture