The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill analyzes local project files such as package.json, requirements.txt, and go.mod, along with source code via grep to detect the development environment. This creates an attack surface where malicious instructions embedded in these files could influence the agent's behavior.
Ingestion points: Project configuration files (package.json, requirements.txt, pyproject.toml, pom.xml, build.gradle, go.mod) and source code content analyzed during the context detection phase in SKILL.md.
Boundary markers: Absent; the instructions do not specify delimiters or system-level instructions to separate untrusted project content from agent instructions.
Capability inventory: File system access (read), code generation, and shell command suggestions.
Sanitization: Absent; the skill does not suggest any validation or sanitization of the content of the detected files before processing.
[EXTERNAL_DOWNLOADS]: The skill references and provides installation commands for official Restate SDKs, CLI tools, and server binaries. These resources are hosted on trusted or well-known platforms including the vendor's GitHub organization (github.com/restatedev), Docker Hub, and standard package registries like NPM and PyPI.
[COMMAND_EXECUTION]: The skill instructs the agent to perform project discovery using grep and provides numerous CLI examples for managing Restate deployments and testing service endpoints via curl and the restate CLI tool.

building-restate-services