etf-premium

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_CONTEXT_INJECTIONEXTERNAL_DOWNLOADSDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests financial data from Yahoo Finance to perform analysis, creating a potential vector for indirect prompt injection.\n
  • Ingestion points: Financial data is fetched via the yfinance library in SKILL.md.\n
  • Boundary markers: There are no explicit delimiters or instructions to ignore embedded content in the ingested data.\n
  • Capability inventory: The skill has network access and the ability to execute shell commands for setup.\n
  • Sanitization: Data is processed for calculations and formatted into tables without specific sanitization of potential text strings from the API.\n- [DYNAMIC_CONTEXT_INJECTION]: The skill uses dynamic context injection (the ! command syntax) in SKILL.md to run a Python script that verifies the presence of necessary dependencies during skill initialization.\n- [EXTERNAL_DOWNLOADS]: The skill provides automated installation of well-known third-party libraries (yfinance, pandas, numpy) from official package registries if they are not already available in the environment.\n- [DYNAMIC_EXECUTION]: The skill utilizes dynamic code execution via the Python exec() function in its environment check command and employs subprocess.check_call to manage package installation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 12:24 AM
Security Audit — agent-trust-hub — etf-premium