teleport-discovery

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

• Third-party content exposure detected (high risk: 0.85). In the “Discovery Status” path, the skill fetches Teleport troubleshooting documentation from https://goteleport.com/docs/.../troubleshooting.md at runtime (“WebFetch” block) and then uses that fetched free-text content to generate resolution steps in the agent’s LLM context.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill performs a runtime WebFetch of the troubleshooting guide at https://goteleport.com/docs/enroll-resources/auto-discovery/servers/troubleshooting.md and instructs the agent to extract and use that content to map failures to resolution steps, so externally fetched content directly governs the assistant's troubleshooting instructions.