game-audio-director

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references two external GitHub repositories (elevenlabs/elevenlabs-mcp and raveenb/fal-mcp-server) as potential MCP integrations for audio prototyping. These are documented as external tools and are not automatically downloaded or executed by the skill itself.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it is instructed to read external project documents, narrative scripts, and art style guides to inform its design decisions. It possesses filesystem capabilities (Write, Edit). However, there are no instructions to bypass safety filters or ignore prior rules.
  • [COMMAND_EXECUTION]: No unauthorized or dangerous command execution patterns were detected. The allowed tools are restricted to standard file and project exploration utilities.
  • [DATA_EXFILTRATION]: There is no evidence of sensitive data harvesting or exfiltration to external domains.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 09:44 PM
Security Audit — agent-trust-hub — game-audio-director