The Agent Skills Directory

[SAFE]: The skill follows security best practices by recommending the use of environment variables for API keys and credentials rather than hardcoding them.
[SAFE]: External dependencies and API endpoints belong to the specific vendor platform (Speak) or well-known services (OpenAI) associated with the skill functionality.
[INDIRECT_PROMPT_INJECTION]: The skill involves migrating user metadata and audio recordings from legacy systems. This processes untrusted data which could potentially contain malicious instructions, though this risk is inherent to data migration tools.
Ingestion points: User data and audio recordings are fetched from legacy databases and storage in references/implementation-guide.md.
Boundary markers: None are present in the code examples to delimit the data from the agent's instructions.
Capability inventory: The skill has access to Bash, Write, Edit, and Grep tools.
Sanitization: No explicit sanitization or validation logic is included in the provided migration examples.

speak-migration-deep-dive