marketing-psychology
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill consists of markdown documentation and Python scripts that perform local text analysis using regular expressions. The scripts use only standard library imports and do not perform network operations, file writing, or command execution.
- [INDIRECT_PROMPT_INJECTION]: The provided scripts ingest external files for analysis, which is a common vulnerability surface for indirect prompt injection if the output is returned to the agent context.
- Ingestion points: File reading in
scripts/persuasion_auditor.py,scripts/cognitive_bias_checker.py, andscripts/pricing_psychology_analyzer.py(viaPath.read_text). - Boundary markers: Absent in the script processing logic.
- Capability inventory: All scripts are restricted to read-only text processing and have no capabilities for subprocess execution, network requests, or file system modifications.
- Sanitization: The scripts use specific regular expressions to filter for marketing-related patterns, which naturally limits the data that can be passed back to the agent.
Audit Metadata