build-vesperfall-review-assets

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external game asset files (PNG, FBX, GLB) which constitutes a data ingestion surface.
  • Ingestion points: The workflow in SKILL.md directs the agent to locate and inspect shipped PNG, FBX, GLB, and texture files within the repository.
  • Boundary markers: None are explicitly defined, though the ingested data consists of binary assets rather than natural language instructions.
  • Capability inventory: The skill executes scripts/validate_pair.py to read file headers and dimensions, and references standard build/linting tools.
  • Sanitization: scripts/validate_pair.py validates the PNG signature and dimensions, and checks for approved file extensions.
  • [COMMAND_EXECUTION]: The skill utilizes a local Python script scripts/validate_pair.py to perform asset validation. The script uses standard libraries and performs safe file-reading operations without shell execution or network access.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 01:30 AM
Security Audit — agent-trust-hub — build-vesperfall-review-assets