game-dev-2d-testing

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: The skill provides standard development and testing workflows. No evidence of malicious behavior, such as unauthorized command execution, data exfiltration, or obfuscation, was found in the instructions or reference materials.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions in SKILL.md require the agent to ingest external data from repository instructions and behavior contracts. This constitutes an ingestion surface, but the skill lacks any high-privilege capabilities or dangerous tools that could be abused through this vector. Evidence: 1. Ingestion points: SKILL.md (repository instructions and behavior contracts). 2. Boundary markers: Absent. 3. Capability inventory: None. 4. Sanitization: Absent.
  • [EXTERNAL_DOWNLOADS]: The reference files references/godot.md and references/phaser.md contain links to official documentation for the Godot and Phaser game engines. These links point to well-known and trusted official domains for the purpose of providing developer guidance.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 12:10 PM
Security Audit — agent-trust-hub — game-dev-2d-testing