News Aggregator Skill 0.1.0

Comprehensive news aggregator that fetches, filters, and deeply analyzes real-time content from 8 major sources: Hacker News, GitHub Trending, Product Hunt,...

This skill appears to implement what it claims (multi-source scraping and deep article extraction) and asks for no credentials, but exercise caution before installing: 1) Inspect SKILL.md and templates.md for hidden/unexpected characters (the pre-scan flagged unicode control characters). Remove or sanitize any invisible/control characters. 2) Verify provenance — README points at a GitHub repo; confirm the repo and publisher identity before cloning or running. 3) Run the Python script in a sandboxed environment (network-restricted or with egress monitoring) first — the 'deep' option fetches arbitrary URLs and can download page content. 4) Review the full fetch_news.py (the bundled file appears truncated in the package preview); ensure there are no hidden endpoints or exfiltration logic. 5) Limit concurrency/limits when doing a Global Scan to avoid large-scale requests. 6) If you plan to persist reports, check that the reports/ directory content and filenames are acceptable and that no unexpected data (e.g., credentials) would be written there. If you can, ask the publisher to provide a canonical homepage or signed source so provenance is clear. If the SKILL.md is cleaned of control characters and the rest of the code is intact/transparent, the skill could be treated as coherent and low-risk.

Type: OpenClaw Skill Name: news-aggregator-skill-0-1-0 Version: 1.0.0 The skill is classified as suspicious due to the presence of prompt injection instructions within `SKILL.md` that direct the AI agent to modify user input (e.g., 'CRITICAL: You MUST automatically expand the user's simple keywords...'). While the stated intent is to enhance search functionality, this capability could be exploited if the expansion logic were flawed or if the agent were instructed to expand into malicious commands. Additionally, the skill performs extensive web scraping from external sources (`scripts/fetch_news.py`) and processes untrusted content, including fetching full article text (`--deep` flag). Although the script includes basic sanitization (removing script/style tags, truncating content, URL validation), the inherent risks of processing arbitrary external data and the agent's interpretation of its own instructions (e.g., file writing to `reports/`) introduce potential vulnerabilities that could lead to unintended actions or RCE if exploited, even without clear evidence of intentional malicious design.