bird-hardened

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt documents and encourages passing authentication cookies/tokens directly via CLI flags like --auth-token / --ct0 and cookie extraction, which would require the LLM to emit secret values verbatim in commands or code.

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly fetches and ingests user-generated X/Twitter content (see SKILL.md commands like "bird read ", "bird thread", "bird replies", "bird search", and "bird news"), so the agent will read untrusted third-party posts that could indirectly inject instructions influencing follow-up actions (e.g., replies, likes, unbookmarking).