bird

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly documents using flags like --auth-token / --ct0 to pass cookie/auth tokens directly, which would require the agent to include secret cookie values verbatim in generated commands or outputs, creating an exfiltration risk.

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 reads public X/Twitter content (tweets, threads, replies, searches, user timelines, trending/news) — user-generated, untrusted third-party data — and the agent is expected to read/interpret that content as part of its workflow.