The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions and does not include any executable scripts or code files.
[PROMPT_INJECTION]: No direct prompt injection, safety bypass, or role-play instructions were found. The skill uses standard instructional language.
[PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it is designed to process and audit data from external websites.
Ingestion points: Untrusted external content from target websites (SKILL.md).
Boundary markers: No explicit delimiters or instructions to ignore embedded commands in the source data are provided.
Capability inventory: No high-risk capabilities such as file system writes, shell access, or external network POST requests are present in the skill.
Sanitization: No sanitization or content filtering is implemented in the provided instructions.

seo-audit