brand-language-codifier
Warn
Audited by Snyk on Aug 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). SKILL “brand-language-codifier” gathers and “scraped keyless” external pasted/scraped brand material via
scripts/connectors/firecrawl.pyand treats it as untrusted input, so outsider-authored free text can enter the runtime through those scraped/pasted sources before codifying voice/naming.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata