research-brand
Warn
Audited by Snyk on Mar 31, 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.md process explicitly instructs the agent to crawl the given company URL and run web searches (see "Crawl the website" and "Search the web" steps) pulling content from public sites like Crunchbase, LinkedIn, app stores, blogs and reviews that the agent must read and synthesize into the brand_dna.md, so untrusted third‑party content can influence its decisions and outputs.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata