The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run a local Python script, campaign-tracker.py, to manage and retrieve campaign history for specific brands. This execution is scoped to the internal plugin directory.
[INDIRECT_PROMPT_INJECTION]: The skill audits external websites and processes data from SEO tools, which presents an attack surface where malicious content on a target site could attempt to influence the agent. 1. Ingestion points: Audited website URLs, Google Search Console reports, and PageSpeed Insights data. 2. Boundary markers: None explicitly defined in the provided instructions to separate external data from agent instructions. 3. Capability inventory: The skill can read local files, execute internal Python scripts, and generate audit reports. 4. Sanitization: No specific sanitization or escaping of external website content is described in the workflow.

technical-seo