The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from multiple sources including local context files and external performance data (CSV or API output).
Ingestion points: Reads .agents/product-marketing-context.md and processes performance data provided by users or APIs.
Boundary markers: The skill does not define specific delimiters or instructions to ignore commands embedded in the ingested data.
Capability inventory: The skill specifies tool integrations for managing Google Ads, Meta Ads, LinkedIn Ads, and TikTok Ads, which include commands to list, get reports, and create campaigns.
Sanitization: There are no explicit instructions to sanitize or validate the external data before it is incorporated into the prompt or used for tool parameters.
[COMMAND_EXECUTION]: The skill documentation includes examples of executing local scripts and CLI tools (e.g., node tools/clis/google-ads.js) to interact with advertising platforms. While these are part of the intended functionality, they represent a significant capability that interacts with the user's environment.

ad-creative