The Agent Skills Directory

[SAFE]: The skill demonstrates secure credential handling by utilizing .env files for API keys and explicitly instructing the agent to add these files to .gitignore to prevent accidental exposure in repositories.
[SAFE]: The HTTP client configuration includes interceptors designed to log only metadata (HTTP methods, URLs, and status codes) while specifically avoiding the logging of sensitive contact data or credentials.
[INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of data from the Apollo.io external API, which represents a potential surface for indirect prompt injection if the API source is compromised.
Ingestion points: API response data is ingested and processed within src/apollo/dev-client.ts and the MSW mock handlers.
Boundary markers: No specific boundary markers or "ignore instructions" delimiters are implemented in the provided code templates for processing API data.
Capability inventory: The skill environment allows for Bash, Write, and Edit operations.
Sanitization: The provided implementation examples do not include explicit sanitization or validation logic for the content received from the external API endpoints.

apollo-local-dev-loop