skills/nexscope-ai/nexscope-ecommerce-skills/ecommerce-amazon-keyword-search-history/Gen Agent Trust Hub
ecommerce-amazon-keyword-search-history
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves data from an external API proxy which is then displayed to the agent, creating a surface for indirect instructions.
- Ingestion points: The script
scripts/amazon_keyword_search_history.pyfetches search volume data from the endpoint specified by theNEXSCOPE_PROXY_BASEenvironment variable. - Boundary markers: There are no explicit boundary markers or instructions to the agent to ignore embedded commands when processing the JSON response or the printed summary.
- Capability inventory: The skill script has the ability to write JSON data to the local file system (within the
nexscope/directory) and perform outbound network requests viaurllib.request. - Sanitization: The script parses the API response as JSON but does not perform any sanitization or filtering on the text content before printing it to the agent's output buffer.
- [COMMAND_EXECUTION]: The skill requires the agent to execute a Python script (
scripts/amazon_keyword_search_history.py) with user-provided parameters passed via the command line. - Evidence: The instructions in
SKILL.mddirect the agent to invoke the tool usingpython scripts/amazon_keyword_search_history.py '<JSON params>'.
Audit Metadata