The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and analyze project files, including build configurations and application manifests. This creates an attack surface where instructions embedded in a project's source code could potentially influence the agent's behavior during a development session.
Ingestion points: SKILL.md (Read the actual build files and app manifests before editing).
Boundary markers: Not specified for external file content.
Capability inventory: File system access, shell command execution (cargo, npm, tauri), and network access for packaging.
Sanitization: No explicit sanitization or filtering mentioned for ingested file content.
[EXTERNAL_DOWNLOADS]: The skill references official Tauri templates and command-line tools obtained via standard package managers like npm, yarn, pnpm, and bun. These operations target well-known public registries and are necessary for the development tasks described.

desktop-gui-dev