copywriting

Pass

Audited by Gen Agent Trust Hub on Apr 8, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill evaluates and processes potentially untrusted data from local repository files, creating a surface for indirect prompt injection attacks.\n
  • Ingestion points: Local project files targeted during the 'Discover brand voice' and 'Read all copy-bearing files' steps, such as READMEs, landing page components, and product descriptions.\n
  • Boundary markers: The instructions do not define any specific delimiters or instructions to isolate the ingested text or to warn the agent against following instructions found within those files.\n
  • Capability inventory: The skill leverages core agent capabilities for reading files and generating/rewriting text based on analyzed content.\n
  • Sanitization: No sanitization, validation, or filtering mechanisms are specified for the content read from the files.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 8, 2026, 04:58 PM