The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses curl to interact with API endpoints and provides shell snippets to the agent to perform these actions.
[COMMAND_EXECUTION]: Instructs the agent to source a local configuration file (.env.local) using shell commands to load environment variables.
[DATA_EXFILTRATION]: Performs network operations via curl to a destination determined by the LAYERPROOF_BASE_URL environment variable, which is not included in the list of whitelisted domains.
[PROMPT_INJECTION]: The skill ingests untrusted data from external API responses (such as preset names, descriptions, and voices) which are then processed by the agent. This represents an indirect prompt injection surface.
Ingestion points: API responses from the /api/v2/tones endpoints (SKILL.md).
Boundary markers: No delimiters or safety warnings are specified to isolate the untrusted API content from the agent's instructions.
Capability inventory: The skill utilizes network communication capabilities via curl (SKILL.md).
Sanitization: There is no evidence of data validation or sanitization for content retrieved from the external API endpoints.

tones