seo-plan
Pass
Audited by Gen Agent Trust Hub on Aug 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it processes untrusted data from user inputs and optional external competitive intelligence tools (DataForSEO) to generate SEO strategy documents.
- Ingestion points: External data retrieved via DataForSEO MCP tools and user-supplied business descriptions as mentioned in
SKILL.md. - Boundary markers: There are no explicit delimiters or specific instructions for the agent to treat ingested data as distinct from the skill's own operational instructions.
- Capability inventory: The skill possesses the capability to write multiple strategic documents to the file system, including
SEO-STRATEGY.md,COMPETITOR-ANALYSIS.md, andCONTENT-CALENDAR.md. - Sanitization: No evidence of input validation or output escaping mechanisms was found in the provided instructions or templates.
Audit Metadata