twitter-workflow

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly instructs the agent to fetch and read public, user-generated Twitter/X content using twitter-cli commands (e.g., "twitter-cli tweet ", "twitter-cli timeline", "twitter-cli search"), and to use that content to draft replies/posts and inform posting decisions, exposing it to untrusted third-party input that could inject instructions indirectly.