historical-market-cap
Warn
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS] (MEDIUM): The skill's setup instructions guide users to download the
octagon-mcppackage vianpx. The authorOctagonAIis not in the trusted source list, making this an unverified external dependency. Evidence: Installation commands inREADME.mdandreferences/mcp-setup.md. - [REMOTE_CODE_EXECUTION] (MEDIUM): The skill configures the agent to execute the
octagon-mcptool. Running unverified code from an external package allows for arbitrary command execution within the agent's environment. - [COMMAND_EXECUTION] (MEDIUM): Setup documentation recommends running shell commands (e.g.,
env,cmd /c,npx) to configure environment variables. While necessary for the tool, these instructions could be leveraged to execute malicious payloads if the user-provided inputs are not carefully managed. - [PROMPT_INJECTION] (MEDIUM): This finding refers to Category 8 (Indirect Prompt Injection). The skill ingests untrusted data from external financial sources via the
octagon-agenttool. 1. Ingestion points:octagon-agenttool (referenced inSKILL.md). 2. Boundary markers: Absent; no specific delimiters or ignore-instructions warnings are provided. 3. Capability inventory: The data is used for analysis and summary, influencing the agent's output and reasoning. 4. Sanitization: Absent; no evidence of filtering or escaping external data before it enters the context.
Audit Metadata