build-and-deploy
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
Bashtool to runnpm run buildandnpx evenhub pack. These commands are standard operations within the Even Hub development ecosystem and align with the skill's stated purpose. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the
app.jsonconfiguration file and interpolates thenamefield into shell command arguments. This creates a potential attack surface where a maliciously crafted project file could attempt shell injection. - Ingestion points: The skill reads the
app.jsonfile from the project root directory during the validation step. - Boundary markers: There are no explicit markers or instructions used to delimit the file content or warn the agent against executing instructions found within the data.
- Capability inventory: The skill leverages the
Bashtool for building, packaging, and verifying the application output. - Sanitization: The instructions include a transformation step that directs the agent to lowercase the application name and replace spaces with hyphens before using it as a filename in the command line.
Audit Metadata