The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes and analyzes untrusted technical content (Markdown articles) provided by the user, which could contain malicious instructions designed to override agent behavior or exfiltrate context during the audit process.
Ingestion points: The scripts scripts/audit_seo.py and scripts/generate_llmstxt.py read content from local files and directories specified by the user or agent at runtime.
Boundary markers: The skill does not employ specific delimiters or "ignore instructions" warnings when processing the body of the Markdown files.
Capability inventory: The skill possesses the ability to read local files, output audit reports to the terminal, and write to a user-specified output file for the llms.txt generator.
Sanitization: The Python scripts perform regex-based analysis but do not include sanitization or validation logic to filter out potential prompt injection attempts within the content body.

seo-optimizer