longbridge-ark-analysis
Warn
Audited by Snyk on May 15, 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 SKILL.md explicitly mandates running WebSearch against open public sources for TAM, Wright's‑Law learning rates, management narrative, and other third‑party reports (see "Workflow" step 3 and the "WebSearch fallback" table), and requires the agent to ingest and act on those web-sourced figures in suitability scoring, cost-curve construction, and scenario modeling—so it clearly consumes untrusted public web content that can materially influence actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata