vercel
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to use
npx @useclawlink/cli, which downloads and executes the CLI tool from the NPM registry. This is a standard execution pattern for developer tools, and the package is provided by the skill's official author, clawlink-hq. - [COMMAND_EXECUTION]: The skill uses shell commands to interact with the Vercel API through the ClawLink CLI. It stores user credentials in the local directory at
~/.clawlink/credentials.jsonto maintain the session. - [INDIRECT_PROMPT_INJECTION]: The skill reads data from external Vercel project metadata, which could theoretically contain instructions intended to influence the agent.
- Ingestion points: The agent ingests data through actions such as
vercel_get_projectsandvercel_get_deployments(found in SKILL.md). - Boundary markers: No explicit delimiters or specialized parsing instructions are provided to separate data from instructions.
- Capability inventory: The skill has the capability to perform network requests via the CLI and write to the local file system (SKILL.md).
- Sanitization: There is no evidence of sanitization for the data retrieved from the Vercel API before it is processed by the agent.
Audit Metadata