The Agent Skills Directory

[DATA_EXPOSURE_&_EXFILTRATION]: No credential leaks or unauthorized data access detected. The skill uses structured tools to access Search Console data and keyword metrics within its intended SEO research scope.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data (SERP results and keyword discovery), which is a standard surface for indirect prompt injection.
Ingestion points: Data returned from tools like research_keywords and get_serp_results (SKILL.md).
Boundary markers: Not explicitly used to delimit external data from instructions.
Capability inventory: The skill has no high-risk capabilities like file system writes or arbitrary code execution; the save_keywords operation requires explicit user confirmation.
Sanitization: Not explicitly implemented.
[COMMAND_EXECUTION]: No dangerous shell commands or subprocess executions are present.

keyword-research