chief-of-staff
Warn
Audited by Snyk on Jul 26, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.78). This skill reads and summarizes outsider-authored free text from Gmail email bodies/headers and WhatsApp messages fetched at runtime (SKILL.md “Email triage” via
gog gmail searchand “WhatsApp (last 24h)” viassh mini+ sqlite3), then includes that content in the prompt context for the LLM to assemble the briefing.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata