data-validation-reporter
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- COMMAND_EXECUTION (SAFE): The skill includes shell scripts (
bulk_install.sh,install_to_repo.sh) designed to automate the deployment of validator components and configuration files across multiple repositories in a local workspace. These scripts perform standard file system operations and git commits which are documented and intended for administrative automation. - PROMPT_INJECTION (LOW): The skill ingests untrusted data from external sources (e.g., CSV files) and renders it into interactive HTML dashboards via Plotly. This creates a surface for Indirect Prompt Injection (Category 8). Evidence Chain for Category 8: 1. Ingestion points: Data is ingested via
pd.read_csv()as seen inexample_usage.py. 2. Boundary markers: No delimiters or instructions to ignore embedded commands are present in the processing logic. 3. Capability inventory: The skill has file-write capabilities (HTML report generation) and executes local shell commands. 4. Sanitization: The provided templates do not demonstrate explicit sanitization or escaping of data before rendering in the HTML report dashboard.
Audit Metadata