analyse-sellside
Warn
Audited by Snyk on Aug 20, 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). SKILL.md’s required runtime workflow reads outsider-provided free text indirectly by
web_fetching specific third-party pages (e.g., Yahoo Finance, TipRanks, MarketBeat, Zacks, Finviz, StockAnalysis.com, Nasdaq, WSJ, Morningstar), which are populated by non-first-party content and could contain attacker-controlled text on those pages.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill explicitly web_fetches live pages at runtime (e.g., https://finance.yahoo.com/quote/{TICKER}/analysis and https://www.morningstar.com/stocks/{EXCHANGE}/{TICKER}/quote) and relies on those fetched page contents to directly determine the agent's outputs, so these runtime external URLs control the agent's behavior.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata