bird

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). This skill's docs instruct users to pass auth cookies directly via command-line flags (e.g., --auth-token / --ct0), which requires including secret cookie values verbatim in commands and thus risks secret exposure/exfiltration.

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

• Third-party content exposure detected (high risk: 0.85). The required workflow is a CLI that reads tweets/threads/search results from X given a user-supplied URL/ID, so the agent would ingest outsider-authored tweet text (free-form user content) into its LLM context via the runtime GraphQL/API response.