kuaishou-video-extract

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill instructs the agent to prompt for and help set the REDFOX_API_KEY by inserting the actual API key value into export/PowerShell commands (e.g., export REDFOX_API_KEY=<值>), which would require the LLM to handle or emit the secret verbatim.

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

• Third-party content exposure detected (medium risk: 0.30). The runtime workflow posts a user-supplied Kuaishou video URL to RedFoxHub submit/result endpoints and then ingests the provider-returned free-text transcript fields (data.text and data.stampSents[].textSeg) without any requirement to select a specific outsider-authored item first.