agent-data-cli
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
npxto download and execute theagent-dataCLI package and additional skills from theagent-data/skillsGitHub repository. These resources belong to the official accounts of the skill's author. - [REMOTE_CODE_EXECUTION]: Employs
npxto dynamically download and run the latest version of theagent-dataCLI and installation scripts (e.g.,init). This allows for runtime setup and updates of the vendor's tooling. - [COMMAND_EXECUTION]: The skill executes various shell commands using
agent-data,npx, andskillsto manage account setup, CLI installation, and API interactions. It uses flags like--yesto automate setup tasks. - [INDIRECT_PROMPT_INJECTION]: The skill processes output from external APIs via
agent-data call, creating a surface where third-party content could influence agent behavior if the source data contains malicious instructions. - Ingestion points: Output from
agent-data callandagent-data docs(SKILL.md). - Boundary markers: None specified for external data output.
- Capability inventory: Shell command execution via
agent-dataandnpx(SKILL.md). - Sanitization: No specific filtering or sanitization of API response content is described before it is processed by the agent.
Audit Metadata