customer-persona-builder

Pass

Audited by Gen Agent Trust Hub on Apr 25, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The skill consists entirely of Markdown instructions and JSON metadata. No executable scripts (Python, JavaScript, Shell, etc.) are present in the package.
  • [SAFE]: Analysis of the instructions and metadata found no evidence of malicious behavior, obfuscation, or unauthorized data access. The reference to 'infloq.com' is a link to the author's official website.
  • [PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it processes untrusted user data to generate personas.
  • Ingestion points: User-provided inputs defined in SKILL.md arguments (product, market, customer type, and buying context).
  • Boundary markers: None identified in the prompt instructions to delimit user data from instructions.
  • Capability inventory: The skill is configured to use Read and Write tools as specified in the SKILL.md frontmatter.
  • Sanitization: No input validation, escaping, or sanitization logic is present in the markdown-based workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 25, 2026, 12:13 AM
Security Audit — agent-trust-hub — customer-persona-builder