Base Deploy

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

• Third-party content exposure detected (medium risk: 0.65). The required workflow is “Install Foundry” and then run npx skills add base/base-skills, which at runtime fetches/installs external community/provider skill content (public registry/package text) that can be ingested into the agent’s LLM context, making it an outsider free-text injection risk.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's setup directs running a remote installer with "curl -L https://foundry.paradigm.xyz | bash", which fetches and executes remote code during installation and is required for the skill's Foundry-based demo (forge/cast), so it is a runtime external dependency that executes code.