news-extractor
Fail
Audited by Snyk on Mar 4, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 0.90). The skill's examples and usage explicitly show passing Twitter cookies via a --cookie argument (auth_token=xxx; ct0=yyy) and references needing valid cookies for protected content, which encourages embedding secret cookie values verbatim in commands/outputs.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). This skill's required workflow (SKILL.md and scripts/extract_news.py plus the crawlers/* modules) directly fetches and parses open/public third‑party pages (e.g., Twitter/X, Quora, Naver Blog, BBC/CNN etc.) and uses that untrusted, user‑generated content as input to its parsing/decision logic, exposing the agent to potential indirect prompt‑injection from those sites.
Audit Metadata