lintro-verify

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs the agent to query public package registries and external tools (e.g., "npm view version", "brew info ", "pip index versions ") and to compare those external version outputs as part of the required verification workflow, which means the agent will fetch and act on untrusted third-party content from public sources.