inspira-ui
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: 0.80). The SKILL.md explicitly tells the agent to fetch and browse public pages (e.g., https://inspira-ui.com/docs/llms-full.txt and https://inspira-ui.com/components), so the agent will ingest and act on open third‑party website content that can influence subsequent tool use and decisions.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The skill explicitly tells the user/agent to fetch https://inspira-ui.com/docs/llms-full.txt at runtime — an "LLM-optimized" remote document that would be injected/used in the agent context and could directly control prompts or behavior.
Audit Metadata