ss-create-branch

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

• Third-party content exposure detected (high risk: 0.75). SKILL.md describes deriving a branch slug by fetching and summarizing content from user-supplied URLs (requirement/document links) at runtime, which can ingest outsider-authored free text into the agent’s LLM context via the “fetch and summarize” document-reading tool path.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly instructs fetching and summarizing external requirement/document URLs at runtime (e.g., https://tracker.example.com/issues/10442755) to derive the branch slug, so fetched content can directly control the agent's generated instructions.