visualize-lyrics
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process song lyrics provided by the user, which presents a surface for indirect prompt injection attacks where instructions could be hidden in the data.
- Ingestion points: Song lyrics are provided as input signals and processed according to the instructions in SKILL.md.
- Boundary markers: The skill instructions do not define boundary markers (e.g., XML tags or delimiters) to isolate the untrusted lyric data from the agent's core instructions.
- Capability inventory: The skill directs the agent to generate images based on the prompts derived from the lyrics, involving tool execution.
- Sanitization: There is no evidence of sanitization, filtering, or instruction-ignoring logic applied to the input lyrics before they are used to drive tool prompts.
Audit Metadata