kuaishou-account-search

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to help set the REDFOX_API_KEY by inserting the user's API key into shell/PowerShell commands (export/SetEnvironmentVariable), which would require the LLM to accept and output the secret value verbatim.

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

• Third-party content exposure detected (medium risk: 0.30). Runtime path: scripts/search_ks_user.py posts user-supplied account_name (from required workflow Step 1/2 input) to https://redfox.hk/story/api/ksAllData/searchUser, which causes the agent to ingest and display the returned nickname/signature/head_url/cover_img_url/kwaiId fields from that search response.