harness-mint
Warn
Audited by Snyk on Jun 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The required runtime path runs
npx metaharness new ... --template <id> --host <id>, which can fetch/use template/host content from external registries or the public network, and that fetched free-form text would be ingested by the agent’s LLM context via the subprocess output/templates.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata