context7
Warn
Audited by Snyk on Feb 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and applies public documentation from Context7's REST API (see SKILL.md "Fetches up-to-date documentation via Context7 REST API" and scripts/context7.sh which calls https://context7.com/api/v2/search and /docs), so the agent will ingest and act on external, untrusted third‑party content when forming answers.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). This skill calls the Context7 API at https://context7.com/api/v2 at runtime (via scripts/context7.sh) to fetch documentation that is injected into the agent's responses, so remote content can directly control prompts/instructions.
Audit Metadata