marketing-psychology

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill includes a text analysis utility that processes external content, which could potentially contain malicious instructions. Ingestion points: The scripts/psychology-trigger-analyzer.py script takes external marketing copy as input via the --input flag. Boundary markers: There are no explicit instructions or delimiters provided in SKILL.md to guide the agent in distinguishing between data and instructions within the ingested copy. Capability inventory: The skill executes local Python scripts for analysis. These scripts are limited to regex matching and dictionary lookups and do not have network, file-system write, or shell execution capabilities. Sanitization: The input text is processed directly by regex patterns without pre-processing or sanitization.
  • [SAFE]: The skill's primary functionality is informational. All included scripts use standard Python libraries, contain no remote dependencies, and perform no network operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 06:29 AM
Security Audit — agent-trust-hub — marketing-psychology