deploy-app
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for executing common deployment and build commands using well-known tools such as the AWS CLI, Vercel CLI, Docker, and the GitHub CLI. These operations are consistent with the skill's purpose of automating CI/CD workflows.
- [INDIRECT_PROMPT_INJECTION]: The skill processes project configuration files to discover deployment contexts and build scripts, which represents a surface for indirect prompt injection.
- Ingestion points: The agent is instructed to read local files such as
package.json,next.config.js,nest-cli.json,vite.config.js, andvercel.jsonto determine project settings (referenced inreferences/workflow.md). - Boundary markers: No specific delimiters or warnings are provided to the agent to isolate or ignore instructions potentially embedded within these configuration files.
- Capability inventory: The skill possesses capabilities to execute shell commands (e.g., project build and migration scripts) and interact with external cloud service APIs through various CLIs.
- Sanitization: There are no explicit instructions for validating or sanitizing the content of the ingested project files before their data is used to drive agent actions.
Audit Metadata