marketing-psychology
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external marketing copy and pricing data via analysis scripts, creating a surface for untrusted data ingestion.
- Ingestion points: scripts/persuasion_auditor.py, scripts/cognitive_bias_checker.py, and scripts/pricing_psychology_analyzer.py read content from files passed as command-line arguments.
- Boundary markers: No explicit boundary markers or instructions to ignore embedded prompts are present in the script logic.
- Capability inventory: The scripts are limited to file reading and text processing using Python standard libraries (re, json, pathlib); no network, subprocess, or dynamic execution capabilities are present.
- Sanitization: Includes basic removal of HTML tags using regular expression substitution before analysis.
Audit Metadata