render-migrate-from-heroku

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to ask users to paste Heroku config and database connection strings and to call update_environment_variables or otherwise apply those values, which requires the LLM to receive and include secret values verbatim in tool calls/outputs.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). In SKILL.md Step 3B (MCP Direct Creation), the agent passes the user-provided repo URL (repo: user-provided GitHub/GitLab URL) into MCP tool calls such that the workflow can ingest repository content/metadata from that outsider-supplied location at runtime.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs users to run a remote install script at runtime via "curl -fsSL https://raw.githubusercontent.com/render-oss/cli/main/bin/install.sh | sh", which fetches and executes remote code and is recommended as the installation path for a tool the skill requires (the Render CLI).