marketing-psychology

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill and its associated scripts perform static analysis of marketing content using regular expressions. No malicious patterns, data exfiltration, or unauthorized command execution were identified.
  • [INDIRECT_PROMPT_INJECTION]: The skill includes scripts (cognitive_bias_checker.py, persuasion_auditor.py) that ingest external text or HTML files for analysis. While this represents an attack surface for indirect prompt injection if the processed content contains malicious instructions, the scripts only perform regex-based pattern matching and do not execute the content or make network requests. The capability is limited to local file reading as part of its primary diagnostic purpose.
  • Ingestion points: The scripts read local files provided as command-line arguments using Path.read_text().
  • Boundary markers: Not explicitly defined in the prompt instructions, though scripts strip HTML tags before analysis.
  • Capability inventory: File read access only; no network, write, or subprocess capabilities are present in the provided scripts.
  • Sanitization: The scripts use re.compile(r"<[^>]+>") to remove HTML tags from input text before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 01:08 AM