The Agent Skills Directory

[SAFE]: The skill uses a modular script architecture where sensitive configuration (API keys and base URL) is loaded from an external file (/Users/jhumanj/clawd/config/apollo.env). This prevents credentials from being exposed in logs or process lists.
[COMMAND_EXECUTION]: The skill executes standard curl commands and helper scripts to interact with the Apollo.io REST API. These operations are within the scope of the skill's documented functionality and use proper shell scripting techniques (e.g., set -euo pipefail and proper variable quoting) to minimize risks.
[DATA_EXFILTRATION]: All network requests are directed to the user-configured APOLLO_BASE_URL (typically api.apollo.io) using standard API headers (X-Api-Key). No evidence of unauthorized data transfer to third-party domains was found.
[PROMPT_INJECTION]: The skill instructions in SKILL.md are purely functional and do not contain any instructions that attempt to override agent safety filters or system prompts.

apollo