scrape-tokens

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill performs legitimate web scraping tasks on well-known public domains (CoinGecko and CoinMarketCap) for the purpose of financial data analysis.
  • [PROMPT_INJECTION]: The skill exhibits a potential surface for indirect prompt injection as it ingests untrusted data from external websites. Ingestion points: Scraped HTML content from CoinGecko and CoinMarketCap (SKILL.md). Boundary markers: Absent; the instructions do not specify delimiters or warnings for processed content. Capability inventory: File system access (saving reports), network access (via browser CLI), and notification capabilities (via Telegram MCP). Sanitization: Absent; the skill extracts and processes raw text strings from the browser DOM. This is documented as a standard characteristic of scraping tools and does not indicate malicious intent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 05:45 AM
Security Audit — agent-trust-hub — scrape-tokens