inbox-assistant
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: 0.90). The skill's Job Alert & Opportunity Research and Deep Mode workflows explicitly instruct the agent to "fetch company website using WebFetch" and to "research external links/companies" (SKILL.md, Job Alert & Opportunity Research / Deep Mode sections), meaning the agent will retrieve and interpret content from arbitrary public websites linked from emails and use that content to influence decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata