storybook-sync

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill's workflow and scripts explicitly fetch and read diffs from the public upstream GitHub repository (https://github.com/storybookjs/storybook.git via scripts/fetch_upstream.sh) and SKILL.md instructs the agent to read and act on those diffs to decide sync actions, exposing it to untrusted third-party content that can influence behavior.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill's fetch_upstream.sh clones/fetches the upstream repository at runtime from https://github.com/storybookjs/storybook.git and the resulting diffs/contents are injected into the agent's analysis workflow (subagent prompts), so remote repository content directly controls the agent's instructions and is a required dependency.