storybook-testing

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to the inclusion of WebFetch and WebSearch tools which allow the ingestion of untrusted external data.\n
  • Ingestion points: The allowed-tools section in SKILL.md includes WebFetch and WebSearch, enabling the agent to retrieve content from external websites.\n
  • Boundary markers: There are no explicit instructions or delimiters defined to separate untrusted external content from the agent's core instructions.\n
  • Capability inventory: The skill possesses filesystem access tools (Read, Glob, Grep) and network access tools (WebFetch, WebSearch). A malicious actor could potentially use indirect prompt injection via a fetched webpage to influence the agent's file operations.\n
  • Sanitization: The skill does not implement sanitization or validation of content retrieved from external sources before processing it.\n- [EXTERNAL_DOWNLOADS]: The skill references various official Storybook and Chromatic dependencies and a GitHub Action. These are well-known services and organizations, and their use in this context is standard and safe.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 08:59 AM