The Agent Skills Directory

[NO_CODE]: The skill consists entirely of Markdown documentation files. It does not include any scripts (Python, JavaScript, Shell), binary files, or configuration files that would perform automated actions or installations.
[INDIRECT_PROMPT_INJECTION]: The skill establishes a workflow for processing external data from files, queries, and APIs. While this creates a potential attack surface, the documentation includes instructions for validation.
Ingestion points: Data enters the context via supplied files, queries, or documented APIs as described in SKILL.md and references/data-and-comparison.md.
Boundary markers: No specific prompt boundary markers or delimiters for untrusted content are defined in the instructions.
Capability inventory: The skill itself contains no subprocess, file-write, or network capabilities; it provides instructions for manual or independent verification of dashboard data.
Sanitization: The skill advises the agent to "Validate malformed values" and independently calculate representative values to verify the accuracy of the displayed information.
[EXTERNAL_DOWNLOADS]: The skill references numerous external resources and dashboard examples from well-known technology organizations and services such as Grafana, Cloudflare, Vercel, and Mozilla. These links are provided for informational and instructional purposes and do not involve automated downloads or remote code execution.

insight-dashboard