migration-companion
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill makes extensive use of shell command execution to perform migration tasks, including running its own bundled scripts, vendor CLI tools (csdx, contentful), and system utilities (python, npm, npx). This is core to its functionality as a migration orchestration tool.
- [EXTERNAL_DOWNLOADS]: The skill automatically manages the installation and upgrade of official npm packages and CLI plugins, such as @contentstack/cli, contentful-cli, and @contentstack/cli-external-migrate. These downloads target official vendor repositories and are necessary for the migration workflow.
- [DATA_EXFILTRATION]: To perform the migration, the skill accesses local Contentful configuration files (~/.contentfulrc.json) to retrieve management tokens. It verifies these tokens by making a secure request to the Contentful API (api.contentful.com). The skill includes robust safeguards, such as a redaction function and explicit instructions, to ensure these credentials are not displayed in the chat or written to logs.
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes and modifies source code from a user-provided local repository. This represents a potential indirect prompt injection surface where maliciously crafted content in the target repository could attempt to influence the agent's behavior during the automated rewrite process.
Audit Metadata