maintain-storybook
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local maintenance and testing scripts via Node.js, specifically 'node scripts/storybook-catalog.mjs' and a suite of test files using 'node --test'. These operations are intended for local catalog management.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and acts upon content from external project files, which represents a potential vector for instructions to influence the agent's behavior.
- Ingestion points: Reads internal documentation such as 'maps/storybook-map/README.md', 'maps/feature-map/README.md', 'DESIGN.md', and Storybook 'index.json' exports.
- Boundary markers: The instructions lack explicit boundary markers or directives for the agent to ignore instructions embedded within the data files it processes.
- Capability inventory: Possesses capabilities to execute shell commands (Node.js), perform Git history checks ('git diff'), and interact with other agent skills for verification.
- Sanitization: No procedures for sanitizing or filtering the content of processed markdown or JSON files are defined in the instructions.
Audit Metadata