kernel-music-song
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill follows its stated purpose of creative songwriting. Analysis of the instructions and metadata revealed no evidence of command injection, data exfiltration, or persistence mechanisms.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text (poems and lyric ideas), which is an inherent part of its creative function. While this creates a surface for indirect prompt injection, no malicious framing or instructions were found.
- Ingestion points: User-provided poems, lyric ideas, or subject matter via the argumentHint.
- Boundary markers: The skill does not define specific delimiters to wrap or isolate user-provided content from the agent's instructions.
- Capability inventory: The skill is scoped to use the Read and Write tools.
- Sanitization: No explicit input validation or escaping instructions are provided for the agent to handle potentially malicious commands inside user text.
Audit Metadata