keyword-research
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the bash tool to execute
curlandjqcommands for API communication and data processing. - [EXTERNAL_DOWNLOADS]: The skill interacts with well-known SEO and search data services, including SemRush (
api.semrush.com), DataForSEO (api.dataforseo.com), and SerpAPI (serpapi.com). - [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: Untrusted data enters the agent context via API responses from SerpAPI (specifically
related_questionssnippets andorganic_results) and SemRush keyword expansions, which reflect content from the public web. - Boundary markers: The instructions do not define delimiters or provide specific guidance to the agent to ignore instructions embedded within the retrieved search data.
- Capability inventory: The skill has access to the
bashtool (viacurl) and the ability to write reports to the filesystem. - Sanitization: There is no evidence of content sanitization, filtering, or escaping for the data retrieved from external search snippets before it is processed by the agent.
Audit Metadata