context7

Warn

Audited by Snyk on Mar 4, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md explicitly instructs the agent to search and read public GitHub issues, pull requests, and discussions (e.g., "Read discussion" and "Check PR for code changes"), which are untrusted, user-generated third-party contents that the agent uses to make decisions and perform follow-up actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 4, 2026, 06:08 AM