contentful
Pass
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
npx @useclawlink/cli, which fetches and executes the CLI tool from the public npm registry at runtime. - [COMMAND_EXECUTION]: The skill relies on shell commands to manage authentication and execute Contentful actions via the ClawLink CLI.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8).
- Ingestion points: SKILL.md (via actions like
contentful_get_content_types,contentful_get_asset, andcontentful_get_editor_interfacewhich read data from external Contentful environments). - Boundary markers: Absent; there are no specific instructions or delimiters to isolate data fetched from Contentful from the agent's primary instruction set.
- Capability inventory: SKILL.md (via the
npx @useclawlink/cli run contentfulcommand which allows the agent to execute write actions and updates in Contentful). - Sanitization: Absent; the skill does not specify any validation or sanitization for the content retrieved from external environments before processing.
Audit Metadata