campaign-analytics
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests external data from user-supplied JSON files for campaign analysis, creating a potential surface for indirect prompt injection if the data contains malicious instructions intended to influence the agent's summary.
- Ingestion points: The scripts
attribution_analyzer.py,funnel_analyzer.py, andcampaign_roi_calculator.pyload data from JSON files provided as CLI arguments. - Capability inventory: The toolset is restricted to mathematical analysis and report generation; all scripts use only the Python standard library and do not possess network, file-writing, or dynamic code execution capabilities.
- Boundary markers: Analysis results are presented in structured text tables or JSON blocks, though explicit "ignore embedded instructions" markers are not included in the report templates.
- Sanitization: Input data is parsed using the standard
jsonlibrary, and the logic is deterministic and numeric-focused.
Audit Metadata