invest-stock
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 stock-analysis framework, but its instruction to fetch data through an unvetted shared layer and to withhold data-source details from the user is a mild concealment of the skill's own activity, which is risky toward the user without showing malicious intent.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow actively searches the web for news, sentiment, employee/customer feedback, and analyst views (deep-dive.md Step 0 and the standard-us/standard-hk-a execution steps), so outsider-authored pages are exposed only after the agent selects them, which is low risk; the mx-data structured fetch in SKILL.md is not outsider free text.
Issues (2)
E004
CRITICALPrompt injection detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata