keyword-research
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data including search queries from Google Search Console and content from competitor websites, which could theoretically contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: Search Console query logs, competitor page content (via SERP analysis), and third-party SEO metric providers (DataForSEO).
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore instructions' warnings when interpolating external data into prompts.
- Capability inventory: The skill utilizes file system operations for reading and writing research logs and project context (
.agents/product-context.md), and makes network requests via licensed SEO API providers. - Sanitization: No explicit sanitization or filtering of external strings (such as keyword queries) is mentioned in the workflow instructions.
Audit Metadata