service-blueprint

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

• Third-party content exposure detected (medium risk: 0.65). The skill is a community package that likely performs “Web research” at runtime, and any fetched public web page text (arbitrary URLs/content) could be ingested as free-form prose into the agent’s LLM context via the research/fetch pipeline; the provided SKILL.md does not show a guaranteed exclusion of such content.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill documentation instructs running "npx skills add j-clegg/service-blueprint-skill" which will fetch and execute remote package code from the upstream repository (https://github.com/j-clegg/service-blueprint-skill) at runtime, so the fetched content can execute remote code and is required to install the full skill.