companiesmarketcap

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

• Third-party content exposure detected (high risk: 0.85). At runtime the skill fetches outsider-authored free text from CompaniesMarketCap public pages/CSVs (e.g., /?download=csv, /{slug}/marketcap/, /{slug}/holdings/) via requests.get(...).text, then parses and includes the extracted table/CSV cell text (company names, tickers, weights, etc.) into the JSON output that is subsequently available to the agent/LLM context.

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

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