game-audio-director

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and interpret external documents, which could potentially contain malicious instructions intended to manipulate the agent's behavior.
  • Ingestion points: The workflow in SKILL.md requires the agent to read the creative director's vision document and search for existing audio documentation.
  • Boundary markers: The skill does not specify any delimiters or instructions to treat external data as untrusted or to ignore embedded commands.
  • Capability inventory: The skill is granted Write and Edit tools, which could be exploited to modify project files if the agent follows instructions embedded in poisoned input data.
  • Sanitization: There are no provisions for sanitizing or validating the content of the documents being processed.
  • [EXTERNAL_DOWNLOADS]: The documentation references external resources and integrations for audio prototyping.
  • The skill points to the elevenlabs/elevenlabs-mcp repository for voice synthesis services.
  • The skill points to the raveenb/fal-mcp-server repository for music and ambient audio generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 08:19 AM