growth
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data, such as website content, search engine results, and competitor pages, to perform SEO audits and GEO citation analysis.
- Ingestion points: Untrusted data enters the agent's context through URL analysis in the
auditrecipe and search result processing in thegeoandkeywordrecipes. - Boundary markers: The instructions do not define specific delimiters or "ignore" directives to prevent the agent from obeying instructions embedded in the analyzed web content.
- Capability inventory: The agent maintains the ability to write to the filesystem (e.g., updating agent journals in
.agents/growth.md) and potentially execute local auditing tools. - Sanitization: No explicit sanitization or filtering logic is provided to handle potential prompt injection patterns within external content.
Audit Metadata