migrate-svelte-zukan
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data from the project's local filesystem, which presents a surface for indirect prompt injection attacks.
- Ingestion points: The agent reads existing project files such as Storybook/Histoire configurations (
.storybook/main.*,histoire.config.*), component story files (*.stories.svelte,*.story.svelte,*.stories.ts), and documentation files (*.mdx,*.story.md). - Boundary markers: No specific boundary markers or instructions to ignore embedded commands within the ingested content are provided to the agent.
- Capability inventory: The skill executes file system operations including creating new catalog files (
.zukan.svelte,.zukan.md), deleting existing tool configurations/stories, and invoking package managers to install dependencies. - Sanitization: There is no evidence of content sanitization or validation performed on the data extracted from the story or documentation files before it is used to generate new files or reports.
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to access documentation from a remote source at
https://oekazuma.github.io/svelte-zukan/llms-full.txt. This domain is associated with the skill's author and provides necessary context for the tool's operation.
Audit Metadata