The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The PlantUML template (templates/c4.puml) references external library files from raw.githubusercontent.com/plantuml-stdlib/C4-PlantUML/. This targets a well-known service and is standard practice for architecture diagramming.
[COMMAND_EXECUTION]: The skill uses git, gh (GitHub CLI), and glab (GitLab CLI) to explore repository configuration and manage issue tracking. These are intended functionalities described in the methodology setup process and are restricted to the local repository context.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from existing project files during its discovery phase, which constitutes a potential injection surface.
Ingestion points: SKILL.md (Step 1) reads AGENTS.md, CLAUDE.md, and CONTEXT.md to identify existing configurations.
Boundary markers: No explicit instructions to ignore embedded commands are present in the ingested files.
Capability inventory: The skill has capabilities to write to the file system (e.g., docs/agents/) and execute issue-tracking commands (gh/glab).
Sanitization: No specific sanitization or validation of ingested content is performed. However, the skill mitigates this risk by presenting all proposed changes to the user and requiring explicit confirmation before execution.
[SAFE]: No malicious patterns, obfuscation, or unauthorized network activity were detected. The skill provides legitimate project scaffolding services following established software engineering methodologies.

setup-ooad