geoly-mcp
Fail
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: HIGHREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill documents the installation of a CLI tool by piping remote shell and PowerShell scripts directly into system interpreters. Evidence: 'curl -fsSL https://geoly.ai/install.sh | sh' and 'powershell -ExecutionPolicy Bypass -c "irm https://geoly.ai/install.ps1 | iex"' in SKILL.md.
- [EXTERNAL_DOWNLOADS]: The skill fetches installation scripts and version metadata from the vendor's website and GitHub repository. Evidence: https://geoly.ai/install.sh and https://raw.githubusercontent.com/geoly-ai/codex-plugins/main/plugins/geoly-mcp/.codex-plugin/plugin.json.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to manage authentication and run the vendor's CLI tools. Evidence: 'codex mcp login geoly' and 'geoly call ' in SKILL.md.
- [PROMPT_INJECTION]: The skill ingests and summarizes content from untrusted external sources, creating a surface for indirect prompt injection. \n
- Ingestion points: Tools like get_prompt_record_detail and get_brand_mention_samples process AI search snippets and brand descriptions from external AI platforms.\n
- Boundary markers: Absent; there are no clear delimiters or instructions to ignore embedded commands in the processed data.\n
- Capability inventory: Includes shell command execution (via codex login) and file writing capabilities (via CLI exports).\n
- Sanitization: Absent; the skill does not specify any filtering or validation for external content before processing.
Recommendations
- HIGH: Downloads and executes remote code from: https://geoly.ai/install.sh - DO NOT USE without thorough review
Audit Metadata