The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external data files such as manifest.json, findings.json, and normalized.json. This provides an attack surface where malicious instructions hidden in the data could influence the agent's behavior. Ingestion points: The skill reads metadata and findings from files located in the output directory of the analytics tool. Boundary markers: No explicit delimiters or instructions to ignore potential commands within these files are provided. Capability inventory: The skill allows execution of the open-analytics CLI tool and generates reports for the user. Sanitization: There is no evidence of sanitization or validation of input data before processing.
[COMMAND_EXECUTION]: The skill is designed to interact with the local system by invoking the open-analytics command-line utility for search visibility and organic traffic analysis.

seo-performance-analysis