contentful-migration
Warn
Audited by Gen Agent Trust Hub on May 12, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONDATA_EXFILTRATIONREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes dynamic context injection (the
!commandsyntax) withinSKILL.mdto automatically execute shell commands when the skill is loaded. Specifically, it runsls migrations/and agrepcommand on local environment files to verify setup. It also enables the execution of Contentful CLI operations vianpx.- [DATA_EXFILTRATION]: The automatedgrepcommand inSKILL.mdtargets sensitive local files such as.envand.env.local. Although the command includes asedfilter to mask secret values in the output provided to the prompt, the execution itself has raw access to these sensitive files.- [REMOTE_CODE_EXECUTION]: The skill is designed to have the agent write TypeScript migration scripts to themigrations/directory and execute them. These scripts have broad capabilities, including the ability to perform arbitrary actions within the migration context and access Contentful management tokens.- [EXTERNAL_DOWNLOADS]: The documentation suggests installingcontentful-migrationandcontentful-clifrom the npm registry. These are official tools provided by the vendor (Contentful) and are considered safe for the intended purpose of the skill.- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it processes external data from Contentful API responses and handles agent-generated migration code. - Ingestion points: Migration scripts stored in
migrations/**and data retrieved from the Contentful Management API viacontext.makeRequest. - Boundary markers: Absent; the skill does not define specific delimiters or instructions to prevent the agent from obeying commands that might be embedded in the data it processes.
- Capability inventory: The skill allows for command execution via
npx, file system interaction for managing migration files, and network communication with the Contentful API. - Sanitization: Not mentioned; there is no specified validation or sanitization for data fetched from external sources before it is used to influence the migration process.
Audit Metadata