context7

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

• Third-party content exposure detected (high risk: 0.80). This skill's SKILL.md and scripts/context7.py explicitly fetch library documentation from the external Context7 API (https://context7.com/api/v2), which the agent ingests and is expected to read and act on to guide coding decisions, exposing it to untrusted third-party content that could contain instructive text.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's runtime client calls https://context7.com/api/v2 to fetch documentation (via search/context endpoints), and that fetched text is intended to be injected into agent context and thus can directly control prompts/instructions.