helvstack-agent-deploy

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). Helvstack’s required runtime workflow ingests outsider-authored free text from the user’s Git repository at step 1 “Inspect before editing” (e.g., README/AGENTS/deployment docs and existing helvstack.yml) and then uses that content for planning, validation, and remote operations.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill includes a runtime installation command that fetches and executes remote code—"go install github.com/ElyzeSolutions/Helvstack/cmd/helvstack@latest"—which the CLI-based workflow depends on.