The Agent Skills Directory

[SAFE]: No security issues detected. The skill instructions follow standard procedures for generating sales assets and use configured tools for legitimate file management and command execution.
[COMMAND_EXECUTION]: The skill is configured to use tools like bash and run_command via its agent configuration (agents/openai.yaml) and frontmatter. These are standard platform tools for this environment and are used according to the described logic for creating and auditing sales documentation.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external data such as customer call transcripts and win/loss reports to inform its output. While this represents a potential attack surface for indirect prompt injection, it is the primary intended function of the skill, and no patterns attempting to exploit this surface were found.

sales-enablement