audience-profile

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious behavior detected. The skill processes brand data and standard marketing information to generate persona documents, consistent with its stated purpose.- [DATA_EXPOSURE]: The skill reads configuration files from the ~/.claude-marketing/ directory. These are application-specific marketing data files and do not include sensitive system credentials or private keys.- [PROMPT_INJECTION]: The skill ingests data from external sources such as brand profiles (profile.json), guidelines (_manifest.json), and SOPs. While this presents a surface for indirect prompt injection, the skill lacks the capabilities (e.g., shell execution, network access, or file writing) required to exploit such an injection for malicious purposes.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 01:18 AM