The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands for building and deploying applications, specifically npm install, npm run build, and domo publish. These are standard operations for the intended migration task.
[INDIRECT_PROMPT_INJECTION]: The skill identifies project origins by scanning external files such as README, package.json, and deployment configurations. Malicious instructions embedded in these files could potentially influence the agent's behavior during the migration process.
Ingestion points: Detection logic parses README, package.json, cloudbuild.yaml, and Dockerfile from the target project (SKILL.md).
Boundary markers: Absent. The instructions do not specify the use of delimiters or 'ignore' instructions when reading the project files.
Capability inventory: The agent is granted capabilities to modify the file system (updating configs, moving files) and execute shell commands (npm, domo).
Sanitization: Absent. There is no explicit requirement to sanitize or validate the content of the project files before the agent processes them.

migrate-googleai