temporal-cortex-scheduling

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

• Third-party content exposure detected (high risk: 0.90). The skill's Open Scheduling / Temporal Links workflow (SKILL.md and references/TEMPORAL-LINKS.md / OPEN-SCHEDULING.md) explicitly instructs the agent to fetch public endpoints (e.g., GET /public/{slug}/availability and /.well-known/agent-card.json) and to read those user-controlled responses to decide which slots to present and whether to call request_booking, which clearly exposes the agent to untrusted third-party content that can influence actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's runtime installation explicitly downloads and executes a platform-specific binary from the GitHub release (https://github.com/temporal-cortex/mcp/releases/tag/mcp-v0.9.1) (and references the repo https://github.com/temporal-cortex/mcp), meaning remote code is fetched and run as a required dependency.