seo-cluster
Pass
Audited by Gen Agent Trust Hub on Jul 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes the
claude-seocommand-line utility to perform specialized tasks. - It runs
render_page.pyfor URL fetching and processing. - It executes
dataforseo_costs.pyto manage API usage costs. - [PROMPT_INJECTION]: The skill possesses an indirect prompt injection attack surface (Category 8).
- Ingestion points: External data enters the context through user-provided seed keywords (
SKILL.md) and organic search results (references/serp-overlap-methodology.md) harvested from Google. - Boundary markers: Collected data is structured into a
cluster-plan.jsonfile and passed as a structured JSON object (cluster_context) when invoking downstream skills. - Capability inventory: The skill has the ability to write multiple files to the workspace, modify existing markdown files to inject internal links (
references/execution-workflow.md), and trigger external content generation skills. - Sanitization: The skill relies on
render_page.pywhich includes SSRF protection mechanisms (url_safety).
Audit Metadata