hyperframes
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [Remote Code Execution & External Downloads]: The skill dynamically fetches and executes its own CLI and workflow components using
npx. For instance, it usesnpx hyperframes skills updateto install specialized workflows andnpx hyperframes@latest upgradeto manage versioning. Executing code downloaded at runtime from an external registry is a security consideration. - [Shell Command Execution]: The skill invokes various command-line utilities using
spawnSync, including the GitHub CLI (gh) and its own launcher script. These tools are used for tasks like retrieving Pull Request metadata and performing website captures. - [Indirect Prompt Injection Surface]: The skill's workflows for creating videos from Pull Requests and websites ingest data from external sources. Malicious content within these sources could potentially influence the agent's behavior during the 'interview' or 'planning' phases.
- [Sub-agent Task Delegation]: The skill dispatches independent child agents with dynamically generated roles and contexts. This architecture delegates tasks to secondary agents using instructions generated at runtime.
Audit Metadata