The Agent Skills Directory

[SAFE]: The skill implements secure practices for credential management by instructing the agent to utilize .env files for API keys rather than hardcoding them.
[SAFE]: All external service integrations, including Ahrefs, Stripe, Shopify, Vercel (agent-browser), and GitHub, target well-known and trusted technology providers for legitimate marketing operations.
[PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it is designed to ingest untrusted external data (client decks, research materials, and web content).
Ingestion points: Reads files from ~/marketing-plans/{client-slug}/materials/ and fetches content via agent-browser.
Boundary markers: The instructions do not explicitly mandate the use of delimiters or 'ignore instructions' warnings when processing these external materials.
Capability inventory: The skill has access to file writing, GitHub repository management, and various marketing automation APIs (Customer.io, Stripe, etc.).
Sanitization: There are no explicit instructions for sanitizing or filtering external content before it is processed by the agent.

marketing-plan