The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data by fetching and analyzing content from external URLs and local file directories. This creates a surface for indirect prompt injection, where an attacker could place malicious instructions in HTML comments, meta tags, or page content to manipulate the AI agent during an audit.
Ingestion points: External URLs and local directories specified by the user in SKILL.md.
Boundary markers: The instructions do not specify the use of delimiters or warnings to the agent to ignore instructions found within the audited content.
Capability inventory: The agent has the ability to read local files, fetch network resources, and execute scripts.
Sanitization: No sanitization or escaping of the ingested web content is defined in the provided instructions.
[DYNAMIC_EXECUTION]: The skill delegates certain analysis tasks to a local Python script (content_quality.py) located in the plugin's script directory, as seen in references/machine-translation-qa.md. This involves executing code from a path constructed at runtime.
[COMMAND_EXECUTION]: The skill defines a command-line interface for performing audits (/seo hreflang audit), which triggers file system reads and network operations to process user-supplied targets.

seo-hreflang