run-build

Pass

Audited by Gen Agent Trust Hub on Nov 12, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill interacts with the chromatic command-line interface to perform visual tests. It emphasizes using repository-pinned versions via npx, yarn, or pnpm to ensure environment consistency and security.
  • [CREDENTIALS_UNSAFE]: Security guidelines for managing the CHROMATIC_PROJECT_TOKEN are clearly defined. The instructions forbid the agent from printing the token, writing it to files, or storing it in shell history, advocating for standard environment variable usage instead.
  • [INDIRECT_PROMPT_INJECTION]: To prevent command injection from untrusted story names or filenames, the skill mandates strict character filtering, requiring the agent to refuse any input containing shell-sensitive characters like quotes, backticks, or dollar signs, and requires user confirmation before execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 12, 2026, 10:31 PM