modal-deploy
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
modal deploycommand to upload and run local Python scripts on the Modal serverless platform. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it can be instructed to deploy files to a cloud environment without adequate safeguards.
- Ingestion points: The
fileinput parameter allows the agent to select which file is pushed to the Modal infrastructure. - Boundary markers: No explicit delimiters or instructions are present to prevent the agent from deploying scripts that may have been altered by untrusted input.
- Capability inventory: The skill possesses the capability to execute shell commands and create persistent remote execution environments (cron jobs) via the Modal CLI.
- Sanitization: No sanitization, validation, or human-in-the-loop verification is performed on the content of the script before it is deployed to the cloud.
Audit Metadata