context7

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

• Third-party content exposure detected (high risk: 0.90). The skill's Core Workflow and scripts/context7.sh explicitly call the Context7 REST API (https://context7.com/api/v2/docs/...) to fetch public library documentation and code examples from third-party sources, which the agent is expected to read and use when answering—meeting the criteria for ingesting untrusted external content.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill performs runtime fetches from https://context7.com/api/v2 (via scripts/context7.sh using curl) to retrieve documentation that is injected into the agent's context, so externally-hosted content can directly control prompts/instructions.