coingecko-and-coinmarketcap-apis

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the curl utility to perform HTTP GET requests to external cryptocurrency data providers and uses jq to parse the resulting JSON payloads.
  • [EXTERNAL_DOWNLOADS]: The skill fetches data from well-known cryptocurrency information services, including CoinGecko, GeckoTerminal, and CoinMarketCap. These references are used solely for retrieving public financial data as part of the skill's primary function.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: Data is ingested from CoinGecko and CoinMarketCap API responses through shell commands in SKILL.md and references/keyless-apis.md.
  • Boundary markers: No explicit delimiters are specified for the agent to separate untrusted API data from the system prompt.
  • Capability inventory: The skill uses shell command execution via curl and jq across its files.
  • Sanitization: The instructions recommend piping output through jq, which ensures data adheres to a valid JSON structure before being presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 02:11 PM
Security Audit — agent-trust-hub — coingecko-and-coinmarketcap-apis