cinefoundry-micro-drama
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local commands such as
node dist/cli.jsandscripts/spark-up.shto run the Cinefoundry production engine. These operations are restricted to the local environment (DGX Spark) and are necessary for the skill's stated purpose of video generation. - [INDIRECT_PROMPT_INJECTION]: The workflow instructions direct the agent to take a user's story idea verbatim and pass it as a shell argument to the production script. This represents an ingestion point for untrusted data into a command execution context. While this creates a potential surface for injection, the skill includes explicit scope-setting steps and local service checks to manage the execution environment.
Audit Metadata