investing

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

• Third-party content exposure detected (high risk: 0.85). El skill hace scraping en runtime de HTML/XML de un tercero (Investing.com) y ese texto se parsea e incorpora al contexto del agente vía el JSON resultante (p.ej., fetch_quote/fetch_historical/fetch_profile/fetch_financials/fetch_dividends/fetch_earnings llaman get() y luego parse_* sobre r.text).

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.70). Flagged because the skill explicitly requires and documents using curl_cffi / curl-impersonate to impersonate a browser TLS fingerprint to bypass Cloudflare's anti-bot protections — i.e., it instructs bypassing a security mechanism even though it doesn't request sudo or modify system files.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)