smart-search
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the execution of a local Python script,
scripts/search_client.py, to interface with the AIsa search API. This is the intended behavior for the skill. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the web and academic sources, making it a surface for indirect prompt injection.
- Ingestion points:
scripts/search_client.pyfetches data from theapi.aisa.oneendpoint, including web snippets and article content. - Boundary markers: The skill instructions do not specify the use of delimiters or explicit 'ignore' instructions for the agent when processing external data.
- Capability inventory: The agent has the capability to run local Python scripts and access network resources through the search client.
- Sanitization: The script performs basic truncation on the content but does not sanitize it for potential prompt injection attacks.
Audit Metadata