company-research

Warn

Audited by Snyk on Mar 12, 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 requires the agent to "Search the web for the company" and to ingest and synthesize content from public third‑party sources (company websites, news, MCA, Tracxn/Crunchbase, Google Business, Glassdoor, Trustpilot, social media/X/etc.) as mandatory inputs in the Research Flow and Source Priority sections, and uses those findings to drive KServe Fit recommendations and BD outreach actions, which exposes the agent to untrusted user‑generated content that could carry indirect prompt injection.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 12, 2026, 03:54 AM
Issues
1