application-optimiser
Warn
Audited by Snyk on Apr 19, 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 Company & Role Research workflow (references/company-research.md and SKILL.md "Company & Role Research") explicitly instructs the agent to run parallel WebSearch/WebFetch against public sites (company websites, Glassdoor, LinkedIn, news, job URLs) and to ingest those third‑party pages as evidence that will shape research briefs and application strategy, exposing the agent to untrusted user-generated content that could carry indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata