event-animation-designer

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external animation timeline data to generate validation findings and implementation plans, creating a potential surface for indirect instructions.
  • Ingestion points: The skill reads user-provided JSON files via the validation script in scripts/validate_animation_timeline.py.
  • Boundary markers: The prompt instructions do not specify delimiters or guidelines for the agent to ignore instructions that might be embedded within the timeline data (e.g., in name or ID fields).
  • Capability inventory: The skill is limited to file reading and local validation logic. It lacks network access or arbitrary command execution capabilities.
  • Sanitization: The validation script performs strict type checking and schema validation, though it echoes input strings (like state and event names) back into its output report.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 08:54 PM