linkfox-temu-manage-product-eu

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill's example usage and invocation format show passing accessToken values inline in command-line JSON (and saving/reading tokens), which would require the LLM/agent to embed secret tokens verbatim in generated commands—an exfiltration risk.

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

• Third-party content exposure detected (medium risk: 0.65). Required runtime path calls the Temu gateway (scripts/_temu_common.py:95-121 → call_temu_api()), then parses and emits the upstream JSON response (scripts/_temu_eu_common.py:89-91 → emit_result()), so any free-text fields inside the outsider-authored Temu response body can be included in the agent’s LLM context via stdout/summary.