The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill utilizes npx @useclawlink/cli to download and run the vendor's CLI tool from the public NPM registry. This is a standard deployment mechanism for this vendor's infrastructure.
[COMMAND_EXECUTION]: The skill is entirely dependent on shell command execution to facilitate interactions between the AI agent and the DataforSEO API via the ClawLink CLI.
[CREDENTIALS_UNSAFE]: The documentation explicitly mentions that the CLI tool stores authentication credentials at ~/.clawlink/credentials.json. While this is standard behavior for the tool, it identifies the location of sensitive credential files.
[INDIRECT_PROMPT_INJECTION]: The skill ingests external data from DataforSEO services which may contain untrusted content.
Ingestion points: Data is retrieved through actions such as dataforseo_get_serp_tasks_ready, dataforseo_get_keywords_data_ready_tasks, and dataforseo_get_backlinks_summary_live (found in SKILL.md).
Boundary markers: The skill does not provide specific boundary markers or instructions to the agent to treat the retrieved SEO data as untrusted or to ignore embedded instructions.
Capability inventory: The skill possesses the capability to execute shell commands and create various tasks within the DataforSEO environment.
Sanitization: There is no evidence of data sanitization or validation performed on the external content before it is processed by the agent.

dataforseo