relic-request-response

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The Authorization example extracts bearer tokens and basic auth credentials from request headers and then returns them verbatim in response bodies, which requires the agent/LLM to read and output secret values directly.

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

• Third-party content exposure detected (medium risk: 0.65). SKILL.md describes runtime request handling where Request.body/readAsString() and query/header values come from the incoming HTTP request (outsider-authored user input), which would be readable free text that could be fed into an LLM context by downstream handlers.