voyage-geo-aeo-analysis
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions include
pip install voyage-geo, which installs an external Python package required for the skill's functionality. - [COMMAND_EXECUTION]: The skill executes multiple CLI commands using the
voyage-geotool, including provider configuration tests and analysis runs. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input and interpolates it into shell commands, creating a potential vulnerability surface.
- Ingestion points: User-supplied brand names, website URLs, and competitor lists are collected and used as parameters in the
voyage-geo runcommand. - Boundary markers: None. The instructions do not include markers or warnings to escape or sanitize user-provided strings before they are passed to the CLI.
- Capability inventory: The skill utilizes shell command execution via the
voyage-geoCLI tool and local file system access to read generated analysis reports. - Sanitization: No sanitization, validation, or escaping logic is defined for the external content provided by the user.
Audit Metadata