generating-app-verify
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to "interview the repo" by observing files, logs, and application behavior. This process involves ingesting untrusted data from the workspace to inform the generation of new skills.
- Ingestion points: Workspace repository analysis.
- Boundary markers: None present in the instructions.
- Capability inventory: Generates skill definitions and executable helper scripts.
- Sanitization: No explicit sanitization or filtering of repository data is specified.
- [DYNAMIC_EXECUTION]: The skill is designed to generate new executable content, specifically helper scripts located in the
helpers/directory, which are used to drive application features. - [COMMAND_EXECUTION]: The skill requires the agent to run the repository's own development commands and diagnostic tools to verify the application's state and behavior.
Audit Metadata