The Agent Skills Directory

[SAFE]: The skill consists of documentation and guidelines for content generation. It does not contain any executable scripts, remote downloads, or hidden commands. All technical examples use standard HTML and JSON-LD patterns.- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and analyze external website content for optimization. This introduces an inherent surface for indirect prompt injection if the analyzed source material contains adversarial instructions. The risk is considered low as the skill does not have capabilities to perform network exfiltration or system-level changes.
Ingestion points: The workflow requires analyzing target website URLs and descriptions (referenced in SKILL.md, CLAUDE.md, and prd.md).
Boundary markers: The instructions do not specify the use of delimiters or 'ignore' commands when processing external text.
Capability inventory: The skill does not include any scripts or tool configurations that allow for file writing, network requests, or shell command execution.
Sanitization: There are no instructions for sanitizing or validating external input before processing.

bencium-aeo