claw-screener

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to download and install the Bun runtime from its official domain (bun.sh). This is a well-known service and the installation method is standard for this runtime.
  • [COMMAND_EXECUTION]: The skill executes TypeScript scripts using the Bun runtime to perform stock screening, technical analysis, and fundamental calculations. These operations are limited to the intended functionality of the tool.
  • [DATA_EXFILTRATION]: The skill communicates with external financial APIs, including data.sec.gov for SEC EDGAR filings and Yahoo Finance for market data. It also fetches S&P 500 ticker lists from a public GitHub repository. These network operations are necessary for the skill's primary purpose and do not target sensitive personal information.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external financial sources, which constitutes an attack surface for indirect prompt injection.
  • Ingestion points: Financial metrics and ticker lists retrieved from the SEC EDGAR API, Yahoo Finance API, and GitHub.
  • Boundary markers: Not explicitly defined in the output prompts.
  • Capability inventory: The skill can read and write local cache databases (sec_cache.db, price_cache.db) and a watchlist configuration file (~/.claw-screener-watchlist.json), and perform network requests to financial data providers.
  • Sanitization: The skill parses structured JSON and CSV data into numeric values for algorithmic analysis (Buffett's formulas and Williams %R), which significantly limits the potential for malicious instruction execution via processed data.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 11:50 AM