tracking-crypto-prices

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface (Category 8).
  • Ingestion points: External market data, including coin names and descriptions, is fetched from the CoinGecko and Yahoo Finance APIs within scripts/api_client.py.
  • Boundary markers: The output formatting logic in scripts/formatters.py does not implement delimiters or explicit instructions to prevent the agent from following potential commands embedded in the fetched data.
  • Capability inventory: The skill is permitted to use Bash(python:*), Read, and Write tools, which provide a vector for exploitation if the ingested data is manipulated.
  • Sanitization: No filtering or sanitization is applied to the content of the API responses prior to presentation to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 03:35 PM