The Agent Skills Directory

[SAFE]: No malicious behaviors, prompt injections, or obfuscation techniques were identified in the skill's instructions or metadata.
[CREDENTIALS_SAFE]: The skill correctly directs users to manage their API keys using environment variables (ACEDATACLOUD_API_TOKEN). It explicitly warns against hardcoding secrets or sharing them in prompts, which is a key security best practice.
[EXTERNAL_DOWNLOADS]: The skill references official vendor domains (acedata.cloud), the skills.sh installation platform, and trusted GitHub repositories for documentation and assets. These are well-known and expected resources for a skill provided by Ace Data Cloud.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text for music generation (lyrics, prompts, and styles). While this represents a data ingestion surface, the interaction is limited to standard API requests and the skill documentation notes that service-side moderation is active.
[COMMAND_EXECUTION]: The agent is instructed to use curl for interacting with the music generation API. These commands are transparent, well-documented, and targeted at legitimate service endpoints.

suno-music