The Agent Skills Directory

[DYNAMIC_EXECUTION]: The skill instructs the agent to write a Node.js script (generate-report.js) using a template and then execute it via the node command. This script dynamically assembles the report and renders charts based on researched data.
[INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes data from external web searches (e.g., job postings, press releases, and corporate news) which are then interpolated into the report and the generation script.
Ingestion points: External research data gathered through Dimensions 1-8, including SAM.gov, USAJobs, and general web search results.
Boundary markers: The skill includes a 'Quality Gate' phase and validation rules to ensure data accuracy and source citation, which serves to mitigate accidental misinformation but not necessarily adversarial injection.
Capability inventory: The agent is capable of writing files to the local filesystem and executing shell commands to install packages and run Node.js scripts.
Sanitization: There is no explicit instruction to sanitize or escape the content retrieved from external searches before it is placed into the dynamically generated script code.
[COMMAND_EXECUTION]: The skill uses the command line to create directories, install dependencies, and execute the generated report script.
[EXTERNAL_DOWNLOADS]: The skill fetches standard packages from the npm registry, including docx, chart.js, and chartjs-node-canvas.

account-intelligence