The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill provides instructions to install the Render CLI by downloading and executing a shell script from a remote source (https://raw.githubusercontent.com/render-oss/cli/main/bin/install.sh) piped directly to the shell (sh). This script originates from the official GitHub organization of a well-known service provider.
[COMMAND_EXECUTION]: The skill directs the agent to execute several shell commands, including render blueprints validate for configuration testing, git remote for repository discovery, and PostgreSQL tools (pg_dump, pg_restore) for data migration.
[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it reads and interprets the content of untrusted local project files to generate service configurations and start commands.
Ingestion points: Local project files such as Procfile, package.json, requirements.txt, and app.json (SKILL.md).
Boundary markers: Absent; there are no instructions to the agent to delimit or ignore instructions embedded within the processed data.
Capability inventory: Shell command execution (git, render, pg_dump) and file writing (SKILL.md, references/data-migration.md).
Sanitization: Absent; the agent extracts values directly from file contents to populate the render.yaml blueprint.

render-migrate-from-heroku