twscrape

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes examples and CLI usage that embed cookies, account passwords, email passwords and proxy credentials directly in commands and code (e.g., add_account with cookies/passwords and proxy URLs with user:pass), which would require the LLM to handle or echo secret values verbatim.

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

• Third-party content exposure detected (high risk: 0.75). At runtime, the skill’s described workflow uses twscrape to fetch Twitter/X content (e.g., tweets/user profiles) and then ingests that returned free-form text (tweet.rawContent / rawContent fields) into the agent’s LLM context for analysis/output.