The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read local files such as .agents/product-marketing.md or .claude/product-marketing.md to gain context before interacting with the user. This creates a surface for indirect prompt injection if these files contain malicious instructions meant to subvert the agent's behavior. * Ingestion points: Local file access to product-marketing.md context files as specified in the 'Initial Assessment' section of SKILL.md. * Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' markers when processing the content of these context files. * Capability inventory: The skill's primary capabilities include generating JavaScript code snippets for Google Analytics 4 and Google Tag Manager, and creating structured tracking plans in Markdown. * Sanitization: There are no instructions for the agent to sanitize or validate the content retrieved from the local context files before using it to inform its output.

analytics