websh
Warn
Audited by Snyk on Jul 22, 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 required runtime flow for
cd <url>spawns a background haiku extraction agent that reads fetched HTML and produces.websh/cache/{slug}.parsed.md, meaning outsider-authored free text from runtime-fetched web pages is ingested into the LLM context during extraction.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata