cloakbrowser
Warn
Audited by Snyk on Jul 11, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). High: the required workflow runs
scripts/fetch.py/eval-js.py/pdf.pywhich navigate to a runtime-supplied URL and then ingest the fetched page’s HTML/visible text (outsider-authored free text) into stdout, which the agent can then place into the LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata