connect
Pass
Audited by Gen Agent Trust Hub on Jun 30, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill's setup instructions direct the user to install official packages from standard registries, such as
composio(PyPI) and@composio/core(NPM). These are well-known libraries for agent tool integration. - [COMMAND_EXECUTION]: The documentation includes standard shell commands for package installation and environment variable configuration to facilitate the integration.
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection because it ingests data from external sources (e.g., reading GitHub issues or emails) and possesses the capability to perform actions based on that content. This is an inherent risk factor for skills designed for cross-app automation.
Audit Metadata