token-pick
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from multiple external sources which could influence its logic or notifications.\n
- Ingestion points: Data is fetched from external APIs (CoinGecko, DexScreener, Polymarket) and via the
WebSearchcapability to find market catalysts and fair-value inputs. A user-supplied variable${var}is also directly interpolated into the thesis context.\n - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the prompt templates when processing this external content.\n
- Capability inventory: The skill possesses the ability to perform network requests (
curl), send notifications (./notify), and write to local log files (memory/logs/).\n - Sanitization: No evidence of input validation or output sanitization for the external data was identified.\n- [DATA_EXFILTRATION]: The skill performs network operations to fetch financial data from well-known services. It communicates with official domains including
api.coingecko.com,api.dexscreener.com, andgamma-api.polymarket.com. These operations are documented neutrally as they are required for the skill's primary function of market analysis.\n- [SAFE]: The skill follows secure practices for handling sensitive information. TheCOINGECKO_API_KEYis managed as an optional environment variable and is properly handled using the platform'srequiresmechanism and conditional shell execution logic.
Audit Metadata