output-style-creator

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes external data and user input to perform file system operations.
  • Ingestion points: Reads instructions from docs/output-style-guidelines.md and collects five wizard responses from the user.
  • Boundary markers: There are no defined boundary markers or instructions to ignore embedded commands within the ingested content.
  • Capability inventory: The skill can write files to the output-styles/ directory and invoke mem_save to persist configuration data.
  • Sanitization: No sanitization, validation, or escaping of the ingested documentation or user input is described in the logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 09:39 AM
Security Audit — agent-trust-hub — output-style-creator