cali-product-execution-critique
Warn
Audited by Snyk on Jul 3, 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). The skill’s Context Audit and URL input path uses
agent_browser: open URL → snapshot → explore flows → snapshot → compare vs spec, which ingests outsider-authored free text from public web pages into the LLM context at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata