The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external sales asset data and closed-lost reasons provided by the user, which serves as an ingestion surface for potentially untrusted content.
Ingestion points: The inventory and losses JSON arrays processed by the resources/enablement-audit.js script in the run() function.
Boundary markers: The skill does not define specific delimiters or "ignore" instructions for the data it interpolates from the user's environment into the audit tool.
Capability inventory: The skill includes a Node.js script capable of local calculation and text formatting. It does not have built-in network exfiltration or file-writing capabilities.
Sanitization: The script uses standard JSON parsing (JSON.parse) but does not implement specific sanitization or filtering for LLM prompt injection patterns within the string values of the inventory or loss reasons.
[EXTERNAL_DOWNLOADS]: The skill references several external sales enablement tools and resources hosted on the author's domain, aajconsult.com.
Evidence: Links to https://aajconsult.com/tools/battlecard-builder, https://aajconsult.com/tools/win-loss-analyzer, and other resources are provided for documentation and context. These represent legitimate vendor infrastructure.
[COMMAND_EXECUTION]: The skill instructions direct the agent to execute a local Node.js script to perform the audit logic.
Evidence: The Workflow and Run the tool sections specify running node resources/enablement-audit.js. The script is bundled with the skill, uses only built-in Node.js modules (fs, process), and does not perform dangerous operations like spawning shell commands or modifying system files.

aaj-sales-enablement