game-developer

Fail

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: CRITICALMETADATA_POISONINGEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [METADATA_POISONING]: The SKILL.md file has been flagged by reputation scanners as malicious (FileRepMalware). The author metadata and documentation links point to external resources that are currently blacklisted.
  • [EXTERNAL_DOWNLOADS]: The skill provides a link to documentation at https://jeffallan.github.io/claude-skills/skills/specialized/game-developer/. This URL has been identified as a malicious domain by automated scanners and is currently blacklisted.
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection due to its handling of untrusted user data.
  • Ingestion points: The skill processes user-supplied game requirements, architecture designs, and mechanic specifications to generate code (SKILL.md).
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between its primary instructions and potentially malicious commands embedded within the user-provided game requirements.
  • Capability inventory: The skill includes templates and instructions for generating complex C# (Unity) and C++ (Unreal Engine) code, as seen in the reference files (references/unity-patterns.md, references/unreal-cpp.md).
  • Sanitization: There is no evidence of input validation or sanitization mechanisms to filter or escape instructions found within external requirement documents before they are used to influence the agent's output.
Recommendations
  • CRITICAL: 1 file(s) identified as malware by FileRep - DO NOT USE
  • AI detected serious security threats
  • Contains 2 malicious URL(s) - DO NOT USE
Audit Metadata
Risk Level
CRITICAL
Analyzed
Sep 5, 2026, 11:39 AM
Security Audit — agent-trust-hub — game-developer