chromatic-themes

Pass

Audited by Gen Agent Trust Hub on Sep 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches documentation, implementation guides, and API references from official sources including the vendor's domain (chromatic.com) and the storybookjs GitHub organization to ensure the agent uses up-to-date configuration patterns.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to fetch external content at runtime and treat it as the authoritative source for generating project configuration, creating a potential attack surface if the remote source were compromised.
  • Ingestion points: URLs defined in reference/docs-map.md, including raw content from GitHub and the vendor's documentation site.
  • Boundary markers: Absent; the skill explicitly directs the agent to ignore its own internal knowledge and rely solely on the fetched content as the authoritative source.
  • Capability inventory: The skill generates and modifies Storybook configuration files (.storybook/main.ts, .storybook/preview.ts) and creates a new modes definition file (.storybook/modes.ts).
  • Sanitization: Absent; no validation or sanitization is performed on the fetched content before it is used to determine the structure and content of generated files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 29, 2026, 09:46 AM