dockerfile-generator
Warn
Audited by Snyk on Mar 4, 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 Stage 2 research workflow in SKILL.md explicitly allows external lookups — including using mcp__context7__query-docs and "Use web search only if Context7 is unavailable" — meaning the agent will fetch and interpret public web/framework documentation (untrusted third‑party content) to decide base images, build steps and other actions that directly influence generated Dockerfiles.
Audit Metadata