market-copy

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns detected. The skill's operations, including reading brand voice documentation and executing local analysis scripts, are well-defined and consistent with its primary purpose of copywriting.
  • [COMMAND_EXECUTION]: The skill uses a local Python script scripts/analyze_page.py to extract voice dimensions from a user-provided URL. This is a standard subprocess invocation for analysis tasks and does not involve elevated privileges or remote script execution.
  • [PROMPT_INJECTION]: The skill processes untrusted content from external URLs to determine brand voice, which represents an indirect prompt injection surface.
  • Ingestion points: External website content scraped via scripts/analyze_page.py.
  • Boundary markers: None explicitly provided for the analysis output.
  • Capability inventory: Text generation and copywriting (low risk).
  • Sanitization: Output from the analysis script is used for dimension scoring rather than direct instruction, reducing the risk of accidental obedience.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 01:06 PM
Security Audit — agent-trust-hub — market-copy