cargo
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill coordinates various AI agents and GTM recipes that process untrusted external data, such as lead lists, company signals, and web research. This represents an attack surface where instructions embedded in that data could influence agent behavior, particularly as no specific sanitization or boundary markers are defined in this router skill.
- [EXTERNAL_DOWNLOADS]: The skill instructions facilitate the installation of the
@cargo-ai/cliglobal npm package and the retrieval of additional skill bundles vianpx skills add getcargohq/cargo-skills. These resources are provided by the vendor and are used for standard platform functionality. - [COMMAND_EXECUTION]: The skill provides numerous CLI commands for the
cargo-aiandghtools to perform workspace management, authentication, and repository interactions. It includes safety-oriented instructions for the agent to seek user confirmation before executing potentially sensitive actions like starring a repository or performing credentialed operations.
Audit Metadata