pp-vagaro

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The document intentionally exposes high-risk capabilities that can be used for data exfiltration or remote control (webhook output delivery, import of browser session JWT/cookies, feedback auto-send, stored credentials, and MCP server registration), so it presents a notable abuse surface if misconfigured or abused.

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

• Third-party content exposure detected (low risk: 0.10). The required runtime workflow uses the vagaro-pp-cli commands (e.g., find, compare, listings, price-check) which sync/search Vagaro business data from the public Vagaro website/API into a local SQLite store, but the skill text itself does not describe any queue/feed or outsider-submission path that the agent would read without first selecting specific Vagaro items.

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

• Potentially malicious external URL detected (high risk: 0.90). This skill's prerequisites instruct running remote installs that fetch and execute code (e.g., "go install github.com/mvanhorn/printing-press-library/library/health/vagaro/cmd/vagaro-pp-cli@latest" and the module "github.com/mvanhorn/printing-press-library/library/health/vagaro/cmd/vagaro-pp-cli"), and the CLI produced is a required runtime dependency—so remote content is fetched and executed as part of using the skill.