lov-deploy-to-vercel
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill performs active command-line operations using the
vercelCLI andcurl. This is the intended purpose of the skill to automate deployment and DNS configuration. - [INDIRECT_PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it processes untrusted input that is later interpolated into shell commands.
- Ingestion points: The skill reads the
namefield from the project'spackage.jsonfile and accepts a user-provided domain as a command-line argument. - Boundary markers: No boundary markers or "ignore embedded instructions" warnings are used when processing these data sources.
- Capability inventory: The skill utilizes shell execution (
bash), file system modification (vercel.json), and network access viacurlto the Cloudflare API. - Sanitization: There is no explicit sanitization or validation of the project name or the domain argument before they are used in shell commands, which could theoretically allow for command injection if the inputs contain shell metacharacters.
Audit Metadata