output-style-creator

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates the creation of output styles by gathering user input and writing it to files, which creates a surface for indirect prompt injection.
  • Ingestion points: The skill ingests untrusted data through a 5-question wizard presented to the user.
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the skill definition to protect the generation process.
  • Capability inventory: The skill has the capability to write files to the output-styles/ directory and utilizes the mem_save tool for persistent storage of the configuration.
  • Sanitization: The instructions do not describe any sanitization, validation, or escaping of the user-provided responses before they are written to the file system or stored in memory.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 04:38 AM
Security Audit — agent-trust-hub — output-style-creator