team-audio
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external project documentation (GDDs, sound bible) and configuration files (.claude/docs/technical-preferences.md) to provide context for sub-agents. This creates a potential surface for indirect prompt injection if these files contain malicious instructions designed to override sub-agent behavior.\n
- Ingestion points: Reads from
design/gdd/,assets/audio/, and.claude/docs/technical-preferences.md.\n - Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are used when passing ingested content to sub-agents.\n
- Capability inventory: Access to
Bash,Write,Edit, andTasktools allows for command execution and file system modifications.\n - Sanitization: No explicit sanitization or validation of the input file content is performed.
Audit Metadata