brand-context
Warn
Audited by Snyk on Feb 22, 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 explicitly asks for a brand website URL and instructs the agent to "scrape these pages using WebFetch" (homepage, about, products, creators, social links) and to use that scraped public website content to infer program maturity and populate the brand-context file, so it ingests untrusted third‑party web content that can materially influence subsequent actions.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill explicitly fetches a user-provided brand website URL at runtime via WebFetch and injects the scraped site text verbatim into the model context to build prompts/brand-context (e.g., the user-supplied site such as https://brand.example), so remote site content can directly control the agent's instructions.
Audit Metadata