setup

Fail

Audited by Snyk on Mar 6, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to ask the user for API keys/secrets and then write those exact values into a generated .env file (and explicitly says to write provided keys directly), which requires the LLM to handle and output secret values verbatim.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).


MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

  • Direct money access detected (high risk: 1.00). The skill is explicitly for a trading/backtesting environment and includes specific financial APIs: it installs ccxt (a crypto exchange API library) and OpenAlgo (Indian markets API) and asks the user to provide and store exchange API keys (API key + secret) and an OpenAlgo API key in .env. These are specific, finance-focused tools that enable authenticated access to exchanges and trading APIs (crypto exchanges and market-data/trading providers). Even though this particular skill only performs setup and not order placement itself, it explicitly configures credentials and libraries used for authenticated trading/market interaction, which falls under Direct Financial Execution risk.

MEDIUM W013: Attempt to modify system services in skill instructions.

  • Attempt to modify system services in skill instructions detected (high risk: 0.90). The skill instructs the agent to run system-level installation commands (including explicit sudo apt-get, sudo make install and writing into /usr) which require elevated privileges and modify the machine's system state.
Audit Metadata
Risk Level
HIGH
Analyzed
Mar 6, 2026, 08:51 AM