common-fetcher
统一采集框架 - 支持 RSS/Web/API，207+ 采集源，AI 评分/分类/摘要
48
60%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./.trae/openclaw-skills/common-fetcher/SKILL.mdW011: 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
This skill is a “common-fetcher” framework that, per SKILL.md, fetches RSS/web/API content from many configured third-party sources (outsider-authored free text), which would then be processed for AI (summary/classification) and thus plausibly ingested into the agent LLM context at runtime via the “Source Layer (抓取源) → Processor Layer (AI 摘要/分类)” path.
- Repository
huangruiteng/CS-Notes
- Revision
0825d79
- 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.