bird

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly shows and encourages passing cookie secrets on the command line (e.g., --auth-token / --ct0), which requires the agent to accept and embed secret cookie values verbatim in commands or outputs.

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md shows the CLI fetches and reads public X/Twitter user-generated content (see "Reading Tweets", "Timelines", "Search", and "replies") which the agent is expected to interpret and which can materially influence actions (see "Engagement Actions" and "Posting"), exposing it to untrusted third-party instructions.