manage-data
Pass
Audited by Gen Agent Trust Hub on Mar 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads and installs the zeroeval Python package from a public registry to provide its core functionality.
- [COMMAND_EXECUTION]: The skill executes several shell commands including pip install, git clone, and various zeroeval CLI commands for environment configuration and dataset management. It provides instructions for using an API key within a git clone URL for backend authentication.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it is designed to ingest and process data from external files and remote repositories which could contain malicious instructions.
- Ingestion points: The skill ingests data from local CSV files, Parquet files in git repositories, and remote datasets pulled via the ZeroEval SDK.
- Boundary markers: There are no explicit boundary markers or instructions to ignore embedded commands within the processed data content.
- Capability inventory: The skill possesses capabilities to push data to remote endpoints and execute git operations.
- Sanitization: No evidence of data sanitization or structural validation is present in the skill instructions or reference files.
Audit Metadata