The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from external files and user-provided inputs, creating a surface for indirect prompt injection where malicious instructions could be embedded in data.
Ingestion points: The skill reads project-wide marketing context from .agents/product-marketing-context.md or .claude/product-marketing-context.md and processes user-supplied landing page URLs and audience descriptions.
Boundary markers: Absent. There are no instructions or delimiters provided to the agent to distinguish between valid marketing data and potentially malicious instructions within the ingested context.
Capability inventory: The skill is primarily instructional and does not include internal executable scripts. It facilitates interactions with advertising platforms via external tool integrations (MCP), which minimizes the risk of local system compromise.
Sanitization: Absent. No validation or filtering logic is specified for the content retrieved from external context files or user inputs before it is processed by the agent.
[EXTERNAL_DOWNLOADS]: The skill provides documentation for installing tracking pixels from well-known services such as Google, Meta, LinkedIn, and TikTok. These are standard industry tools for conversion tracking and are used for instructional purposes for the end-user's website, presenting no risk to the agent environment.

paid-ads