geopolitical-risk

Fail

Audited by Snyk on Nov 21, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (medium risk: 0.30). The skill is a legitimate geopolitical-risk analysis guide, but line 766 lists an OKX crypto exchange as a commodity-futures data source, an unexplained cryptocurrency reference unrelated to the skill's purpose, which the recall-first rule treats as a medium-risk sign.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (low risk: 0.10). The only runtime path that ingests readable web text is the optional Option A news-reading flow, where the agent uses read_url (Jina) to fetch news pages and passes the content to the LLM, which is an arbitrary-web-page fetch that the agent performs without any outsider forcing delivery, so it falls under low.

Issues (2)

E004
CRITICAL

Prompt injection detected in skill instructions.

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
CRITICAL
Analyzed
Nov 21, 2026, 05:36 PM
Issues
2