context7-cli

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

• Third-party content exposure detected (medium risk: 0.65). Outsider free text can enter the agent context via the “find-docs” skill (CLI + Skills mode) that guides the agent to run ctx7 docs and then ingest the returned documentation prose/code snippets (fetched from Context7’s external library sources at runtime).

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

• Potentially malicious external URL detected (high risk: 0.90). The CLI supports installing skills from external repositories (e.g., /anthropics/skills) via "ctx7 skills install", which at runtime fetches Markdown skill files that are used to instruct AI agents and thus can directly control agent prompts.