finance-news
Warn
Audited by Snyk on Aug 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The finance-news skill’s runtime workflow
workflows/briefing-cron.yaml→scripts/briefing.py→scripts/summarize.pyingests outsider-authored free text from configured RSS feed items (e.g., Reuters/WSJ/FT/Bloomberg/CNBC/Yahoo/Tagesschau headlines/titles/links) that are fetched and then summarized via the local LLM routes, with no evidence of requiring user-delivered “specific item” selection first.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The repo includes explicit runtime LLM endpoints (FINANCE_NEWS_QWEN_BASE_URL=http://100.124.155.99:4000/v1 and FINANCE_NEWS_DS4_BASE_URL=http://gx10r-head:8888/v1) referenced in the Dockerfile, README, workflows and troubleshooting docs, showing the skill will call those model HTTP endpoints at runtime to generate briefing text (i.e., external model responses will directly control the agent's output).
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata