m-transition

Pass

Audited by Gen Agent Trust Hub on Apr 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it is designed to ingest and process external CSS data from a project repository.
  • Ingestion points: The skill reads and reviews CSS transition declarations from the user's workspace files.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the CSS data are provided in the skill instructions.
  • Capability inventory: The skill utilizes the agent's ability to read and modify project files to standardize CSS transitions.
  • Sanitization: The skill does not implement validation or sanitization of the input CSS content before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 16, 2026, 08:23 AM