The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch documentation and migration guides from the official vendor domain at https://mastra.ai/llms.txt. It also facilitates the installation of dependencies from the public NPM registry using npm install and npx. These resources are provided by a well-known service associated with the skill's primary purpose.
[COMMAND_EXECUTION]: The skill provides numerous instructions for executing local commands to manage projects and inspect documentation. These include using ls, grep, and cat to read local source files and embedded documentation in node_modules. It also covers running npm install for dependency management, npx @mastra/codemod for version upgrades, and docker run to initialize a database for development testing.
[PROMPT_INJECTION]: The skill contains an indirect prompt injection surface as it processes external content with significant agent capabilities:
Ingestion points: Retrieves remote documentation from https://mastra.ai/llms.txt (SKILL.md, references/remote-docs.md).
Boundary markers: Absent; the instructions do not specify the use of delimiters or 'ignore' warnings for the fetched remote content.
Capability inventory: The skill includes commands for filesystem reading (cat, grep) and package installation/execution (npm, npx) across multiple documentation files.
Sanitization: Absent; there is no mention of validating or filtering the remote content before it is processed by the agent.

mastra