viral-chaser
用户转发/分享抖音、B站、小红书视频链接(v.douyin.com / b23.tv / xhslink.com / xhslink.cn),要求拆解分析时使用（俗称「追爆」）：下载视频、ASR 转写、结构化拆解，产出拆解分析报告。仅产出报告，视频生产需另外委托 content-producer。
68
83%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
High
Do not use without reviewing
Security
2 findings: 1 high severity, 1 medium severity. You should review these findings carefully before considering using this skill.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The skill explicitly instructs users to hand APP ID and Access Token to the agent (小贝) and to have the agent/spawned subagent place them into instance environment variables, meaning the LLM will be required to receive/handle secret credential values in-chat (high exfiltration risk) even if not instructed to inline them in commands.
W013: Attempt to modify system services in skill instructions.
What this means
The skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.
Why it was flagged
Line 26 explicitly instructs the agent to spawn a subagent "IT engineer" to add sensitive credentials into the instance environment variables (i.e., modify the machine's environment/config), which directs the agent to change the host's state and handle secrets—this is an instruction to modify system-level configuration and thus is a security risk.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
Skill.md 的 Step 2/Step 3 runtime 会在“viral-chaser <url>”参数提供的视频 URL 上进行探活、下载视频/提取音频并调用 transcriber.ts 将音频转写成 transcript 文本（LLM 在后续生成追爆报告时读取该文本）。
- Repository
- TeamWiseFlow/xiaobei
- Commit
fdc03d6
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.