rss-ai-reader
Warn
Audited by Snyk on Feb 19, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The SKILL.md and references/config_guide.md explicitly show the tool automatically fetches public RSS/Atom feeds (e.g., hnrss.org, ruanyifeng.com, v2ex.com and arbitrary feed URLs) and passes the article content to Claude/OpenAI to generate summaries and push notifications, so untrusted third‑party content is ingested and can influence model outputs and downstream behavior.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The quickstart/install instructions instruct cloning and running remote code (git clone https://github.com/BENZEMA216/rss-reader.git then python main.py), so the skill requires fetching and executing code from that GitHub repo at install/run time, which constitutes executing remote code and is therefore a runtime risk.
Audit Metadata