swain-init

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

• Third-party content exposure detected (high risk: 0.90). This skill's required workflow explicitly fetches and installs remote, third-party code (e.g., Phase 2.1's curl https://astral.sh/uv/install.sh, Phase 3's pre-commit GitHub repos, and Phase 4.3's "npx skills add obra/superpowers"), which brings untrusted public packages/scripts into the agent environment that the agent will read/execute and that can materially change subsequent actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly runs a runtime installer that pipes a remote script to the shell ("curl -LsSf https://astral.sh/uv/install.sh | sh"), which fetches and executes remote code to provide the required uv runtime for swain scripts.