The Agent Skills Directory

[SAFE]: No malicious patterns or high-risk security concerns were identified during the analysis of the skill's instructions and configuration.
[COMMAND_EXECUTION]: The skill involves the use of command-line tools to interact with SEO reports. The instructions provide specific patterns for using the seo utility to describe and execute report tasks.
Evidence: seo reports describe get-crawl-report --json, seo reports run get-crawl-report --params '{"id":"crawl_example_20260710","includeIssues":true}' --json.
[PROMPT_INJECTION]: An indirect prompt injection surface is present because the skill processes content from previously saved web crawl reports, which contain untrusted data from external websites.
1. Ingestion points: The seo_run_report tool as described in SKILL.md.
1. Boundary markers: Absent; there are no specific instructions to the agent to treat crawl data as untrusted or separate it from system instructions.
1. Capability inventory: Tool access includes seo_list_reports, seo_describe_report, and seo_run_report for report management.
1. Sanitization: None specified in the provided instructions.

get-crawl-report