kahraman-storybook-testing
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes local project files which could potentially contain malicious instructions intended to influence the agent's behavior during documentation or code generation tasks.
- Ingestion points: The skill reads local project files including
.storybook/README.md,.storybook/main.*,.storybook/preview.*, and*.stories.ts(x)to extract project-specific conventions and configurations. - Boundary markers: The instructions do not define specific delimiters or "ignore previous instructions" markers to wrap the content ingested from these project files.
- Capability inventory: The skill uses
Bash read edit writetools (defined inSKILL.md) to read configuration and write or update files like.storybook/README.mdand interaction stories. - Sanitization: There is no mention of sanitizing, escaping, or validating the content read from the project files before it is processed by the agent or written back to the filesystem.
Audit Metadata