team-audio
Pass
Audited by Gen Agent Trust Hub on Mar 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a structured workflow for audio design that is consistent with its stated purpose of managing subagents and compiling documentation.\n- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by reading untrusted data from project-specific directories.\n
- Ingestion points: Reads files from
design/gdd/andassets/audio/(SKILL.md).\n - Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are present in the delegating prompts.\n
- Capability inventory: The skill includes the
Bash,Write,Edit, andTasktools (SKILL.md).\n - Sanitization: No validation or sanitization is performed on the ingested content before it is provided to subagents.\n- [COMMAND_EXECUTION]: While the
Bashtool is enabled in the frontmatter, it is not used within the instruction logic, minimizing the risk of arbitrary command execution.
Audit Metadata