linkfox-temu-returns-refunds-global

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill's examples and CLI usage explicitly show embedding API keys/access tokens directly into command-line arguments and JSON (e.g., export LINKFOXAGENT_API_KEY and passing "accessToken" inline), which requires handling and outputting secret values verbatim.

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

• Third-party content exposure detected (high risk: 0.85). Required runtime path calls Temu via the LinkFox gateway (scripts/_temu_common.py:95-120 → scripts/_temu_global_common.py:65-68 → scripts/_temu_global_common.py:89-91), then prints/summarizes the gateway’s body/parsed JSON into stdout (scripts/_temu_common.py:308-332), which is outsider-authored free text (Temu/partner API responses) that can be ingested by the agent.