byted-kickart-subtitle-extractor

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly asks users to paste ACCESS_KEY_ID/SECRET_ACCESS_KEY into chat and instructs echoing and exporting those environment variables (including ARK_SKILL_API_KEY) so the agent will handle and output secret values verbatim.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). High-risk: the skill documentation explicitly instructs soliciting users' AK/SK via chat and the code logs request headers/authorization to local logs, enabling credential capture and exfiltration.

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

• Third-party content exposure detected (medium risk: 0.30). 在运行时流程“视频字幕提取”中会下载/读取用户提供的公网视频URL并将提取到的字幕文本（captions.text、captions.words[].text）作为{full_text}/{word_rows}展示给用户，字幕文本可由视频内容/来源的外部作者诱导并进入后续SRT生成与输出。

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill makes runtime requests to https://icp.volcengineapi.com (scripts/core/api/iccp/client.py) whose response may include an "install_command" that SKILL.md instructs to execute during the mandatory version-check/update flow, meaning remote content can direct execution of commands.