opentrade-token
Fail
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSCREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill requires downloading and executing a remote shell script using a pattern where curl output is piped directly into the shell (sh). This occurs during initial installation, periodic update checks every 12 hours (gated by a timestamp check in ~/.opentrade/last_check), and as a recovery step for failed commands. The script is hosted at raw.githubusercontent.com/6551Team/openskills/main/skills/opentrade/install.sh.
- [COMMAND_EXECUTION]: The skill instructions direct the agent to interact with the local system by executing the opentrade CLI tool with various subcommands and parameters based on user queries.
- [EXTERNAL_DOWNLOADS]: The skill performs network requests to fetch installation and update scripts from an external GitHub repository.
- [CREDENTIALS_UNSAFE]: The skill instructs the agent to create and read a .env file containing a sensitive API token (OPEN_TOKEN) for the 6551.io platform.
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it processes data from external blockchain sources. Ingestion points: Data returned by the opentrade CLI search and info commands. Boundary markers: None identified in the instructions. Capability inventory: Shell command execution and file system access. Sanitization: None described for the processing of external tool output.
Recommendations
- HIGH: Downloads and executes remote code from: https://raw.githubusercontent.com/6551Team/openskills/main/skills/opentrade/install.sh - DO NOT USE without thorough review
- AI detected serious security threats
Audit Metadata