twitter-mcp

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.80). Most URLs are benign API or localhost callback endpoints, but the raw.githubusercontent.com links point to direct shell installer scripts (one explicit and one templated) from an unverified GitHub user which are high-risk download sources for executables/scripts.

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow for daily digests runs xurl CLI commands (e.g., xurl timeline/mentions/search/posts), whose outputs are X/Twitter content authored by outsiders, and those outputs are then used to draft the final digest in the agent’s LLM context—creating an indirect prompt-injection risk from outsider-authored free text.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill contains a runtime curl | sh installer that downloads and executes code from raw.githubusercontent.com (e.g. https://raw.githubusercontent.com/BofAI/skills/v1.5.12-beta.12/twitter-mcp/install.sh and the BASE_URL https://raw.githubusercontent.com/BofAI/skills/${TAG}/twitter-mcp used by install.sh), so external content is fetched during runtime and executed.