lightfast-sdk
Warn
Audited by Snyk on Apr 25, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's workflow (SKILL.md and command/lightfast-sdk.md) explicitly instructs the agent to call lightfast_proxy_search and lightfast_proxy_call to fetch and act on data from connected third-party providers (GitHub, Linear, Sentry, Vercel, Apollo), which includes user-generated/untrusted content (issues, PRs, comments) that the agent is expected to read and which can influence subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata