linkfox-temu-cancel-order-us

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill's examples and usage explicitly show passing secrets (LINKFOXAGENT_API_KEY and Temu accessToken) directly on the command line / in JSON arguments, which would require the LLM to emit secret values verbatim if asked to construct commands or examples.

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

• Third-party content exposure detected (high risk: 0.75). Required workflow calls Temu gateway at runtime and then prints/summarizes the gateway’s JSON response (including body/errorMsg free text) into the agent’s LLM context via stdout; this response is outsider-authored (Temu system) and can contain arbitrary strings.