seo-orchestrator
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it ingests untrusted data from the web (HTML, rendered DOM, robots.txt, sitemaps) to perform its analysis.
- Ingestion points: Data is retrieved via
WebFetchandseo-crawl-render(Phase 1) and stored in a sharedPageSnapshotfor subagent processing. - Boundary markers: There are no explicit instructions or delimiters mentioned in the orchestration logic to isolate the fetched content from the agent's internal reasoning.
- Capability inventory: The skill uses
WebFetch(network),Read(file access), andTask(sub-task execution). It mitigates risk by explicitly stating that all specialist subagents are read-only and lack access to write or edit tools. - Sanitization: No mention of content sanitization or validation is present in the skill's instructions.
Audit Metadata