contentful
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
npxto fetch and run the@useclawlink/clipackage. This package is the official tool provided by the vendor to interface with the ClawLink service. - [COMMAND_EXECUTION]: The skill defines several shell commands for the agent to execute, including logging in, connecting to Contentful, and performing CRUD operations on Contentful data using the command-line interface.
- [INDIRECT_PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by ingesting content from Contentful which is then processed by the agent.
- Ingestion points: Content entries, assets, and app definitions retrieved from Contentful via the
npx @useclawlink/cli run contentfulcommand. - Boundary markers: No specific delimiters or warnings for the agent to ignore instructions within the retrieved data are present.
- Capability inventory: The skill possesses the ability to read from and write to (archive, publish, update) the connected Contentful environment.
- Sanitization: No sanitization or validation steps are defined for the data retrieved from Contentful before it is processed.
Audit Metadata