vercel-cli
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to use the
vercelCLI for project management tasks. - Specifically, it mentions
vercel env pull,vercel inspect,vercel logs, andvercel lsas valid operations. - [INDIRECT_PROMPT_INJECTION]: The skill allows the agent to ingest untrusted data from application logs, which could contain adversarial instructions targeting the agent.
- Ingestion points: The
vercel logs <url>andvercel inspect <url>commands retrieve data directly from the Vercel platform's runtime environment (SKILL.md). - Boundary markers: The instructions do not provide delimiters or warnings to the agent to treat the log content as untrusted data.
- Capability inventory: The agent is equipped to execute shell commands via the Vercel CLI to manage environment variables and inspect deployment states.
- Sanitization: There are no instructions for the agent to sanitize or filter the content of the logs before processing them.
Audit Metadata