campaign-analytics
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides documentation, templates, and Python scripts for offline marketing performance analysis. The code uses only the Python standard library and contains no malicious logic, obfuscation, or unauthorized network operations. All scripts are deterministic and focus on mathematical calculations for campaign data.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external JSON data from local files, which serves as a potential ingestion surface for malicious instructions if the resulting analysis reports are subsequently processed by an AI agent.
- Ingestion points: attribution_analyzer.py, funnel_analyzer.py, and campaign_roi_calculator.py load data from user-specified local JSON files via command-line arguments.
- Boundary markers: Absent. The scripts do not wrap output in specific delimiters or provide "ignore instructions" warnings for the data fields included in reports.
- Capability inventory: No subprocess calls, exec/eval, file-write, or network operations are present in any of the scripts (attribution_analyzer.py, funnel_analyzer.py, or campaign_roi_calculator.py).
- Sanitization: Absent. String values from input data are included directly in generated text and JSON reports without escaping or filtering.
Audit Metadata