design-system-lead
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The
scripts/adoption_analyzer.pyscript ingests data from external CSV files to generate adoption reports that are processed by the agent.\n - Ingestion points: Data is loaded from CSV files in the
load_adoption_csvfunction withinscripts/adoption_analyzer.py.\n - Boundary markers: The script does not implement specific delimiters or instructions to prevent the agent from following directions potentially embedded within the CSV data fields.\n
- Capability inventory: The skill's scripts are restricted to the Python standard library and do not perform network requests, execute shell commands, or use dynamic evaluation functions like
eval()orexec().\n - Sanitization: Input from the CSV file is not sanitized or validated for malicious instructions before being included in the generated report output.
Audit Metadata