vercel
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill interacts with the local system by executing the
vercelCLI tool to perform various project management tasks. - [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection by ingesting potentially untrusted data from Vercel environments.
- Ingestion points: Data is ingested through actions defined in
manifest.yamlincludingdeployment_files.read,sandbox_files.read, andobservability.read(logs). - Boundary markers: The instructions do not specify the use of clear delimiters or warnings to ignore instructions embedded within the ingested data.
- Capability inventory: The skill has significant capabilities listed in
manifest.yaml, such asdeployments.publish(deploying code),purchases.execute(financial transactions),sandboxes.execute(code execution), andcli.execute(arbitrary CLI commands). - Sanitization: There is no evidence of content sanitization or filtering for the data retrieved from external Vercel sources.
Audit Metadata