The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local shell commands such as git log, git tag, git branch, cat, and a project-specific script ./scripts/octo-state.sh to gather project status and recent activity.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from project files, creating an indirect prompt injection surface. * Ingestion points: Content is read from .octo/STATE.md and .octo/ROADMAP.md (SKILL.md, Phase 2 and 3). * Boundary markers: None identified; the skill directly parses and displays content from these files without delimiters or instructions to ignore embedded commands. * Capability inventory: The skill has shell execution capabilities through git and project-local scripts. * Sanitization: No validation or sanitization of the ingested file content is performed before processing or display.

skill-status