acestep
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it processes untrusted user data (prompts and lyrics) and interpolates them into shell commands for the
music_gen.pytool. - Ingestion points: The
--promptand--lyricsarguments inSKILL.mdaccept external text strings that are passed directly to a local execution tool. - Boundary markers: The skill does not explicitly define delimiters or instructions to ignore embedded commands within the processed lyrics or prompts.
- Capability inventory: The skill facilitates file system writes (output mp3/wav files) and network operations (interaction with RunPod API via
music_gen.py). - Sanitization: There is no mention of input sanitization or escaping for the user-provided prompt/lyric data before it is passed to the subprocess call.
Audit Metadata