viral-chaser
下载分析抖音/B站/小红书爆款视频，生成追爆报告。仅产出报告，脚本另外使用 video-product 技能根据 追爆报告.md 生成。
60
72%
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
Fix and improve this skill with Tessl
tessl review fix ./crews/main/skills/viral-chaser/SKILL.mdSecurity
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 instructs the user to hand APP ID and Access Token to the agent and directs the agent to spawn a subagent to write those credentials into instance environment variables, which requires the LLM to receive and forward secret values (potentially verbatim), creating an exfiltration risk.
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
The skill explicitly instructs the agent to "spawn an IT engineer" subagent to add sensitive credentials into the instance environment/service configuration, which directs the agent to modify the machine's environment and potentially service config (a state-changing, possibly privileged action).
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
Outsider free text is fetched/derived from the runtime input URL’s target platform (e.g., XHS Douyin/Bilibili HTML/JSON/ASR text) and then ingested into the agent’s context via the required workflow: `viral-chaser <url>` outputs `transcript.text` and quoted metadata on stdout, which the agent later uses to generate the Markdown report; this is not user-authored text.
- Repository
- TeamWiseFlow/xiaobei
- Commit
bcef823
- 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.