songwriting-notebook

Pass

Audited by Gen Agent Trust Hub on Oct 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input, such as lyric drafts and voice memo transcripts, which are formatted and can be saved to an external notes application.
  • Ingestion points: The skill accepts user-provided text for song ideas, lyrics, and transcripts as described in the "What to ask for" section of SKILL.md.
  • Boundary markers: The output is structured using Markdown, but there are no explicit instructions for the agent to treat the user's song content as non-executable data or to ignore embedded commands.
  • Capability inventory: The skill mentions the ability to interface with a "notes tool" or the "Scratchpad connector" to save the resulting notebook (SKILL.md, "Saving the note" section).
  • Sanitization: The instructions direct the agent to keep spelling and slang "exactly as written," which ensures fidelity to the songwriter's intent but does not include sanitization of the input content.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 28, 2026, 12:16 AM