marketing-seo-specialist
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for ingesting and analyzing external data from websites, competitor strategies, and search engine APIs, which represents an indirect prompt injection attack surface.\n
- Ingestion points: Technical SEO audits involving site crawls (SKILL.md, Phase 1), competitive landscape identification (SKILL.md, Phase 1), and Search Console performance analysis.\n
- Boundary markers: The instructions lack explicit delimitation or 'ignore instructions' wrappers for the external content being analyzed.\n
- Capability inventory: The skill primarily consists of instructional prompts; the provided shell script (scripts/run.sh) is a standard entry-point wrapper and does not perform dangerous operations.\n
- Sanitization: No validation or sanitization of the external data is specified in the audit or research workflows.
Audit Metadata