skills/viralcode/openwhale/technews/Gen Agent Trust Hub

technews

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs its primary function of aggregating and summarizing news from public RSS feeds and articles without suspicious side effects.
  • [EXTERNAL_DOWNLOADS]: Fetches data from techmeme.com, nitter.net, and hn.algolia.com. These are well-known technology news and social media services.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted content from the open web (news articles). While this constitutes a surface for indirect prompt injection, the behavior is expected for a news aggregator and the risk is mitigated by the skill's specific focus on content extraction rather than command processing.
  • Ingestion points: scripts/techmeme_scraper.py (RSS feed parsing) and scripts/article_fetcher.py (Web content retrieval).
  • Boundary markers: Absent; the skill passes raw or truncated text to the agent without specific delimiters or isolation instructions.
  • Capability inventory: Network requests via the requests library and file system access for local caching in ~/.cache/technews/.
  • Sanitization: Implements basic HTML tag stripping using regular expressions in the scraper module.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 12:14 AM
Security Audit — agent-trust-hub — technews