kiwi-go-agent
Fail
Audited by Gen Agent Trust Hub on Feb 21, 2026
Risk Level: CRITICALPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION] (LOW): Indirect Prompt Injection surface detected in the title generation logic. Untrusted input is directly embedded into the prompt template, allowing for potential override of the title generation instructions.\n
- Ingestion points: The
contentvariable inreferences/langchain-chains.md(read frominputs["content"]).\n - Boundary markers: Absent. The user-provided text is appended directly after a label in
prompt.txt.\n - Capability inventory: The interpolated prompt is used in
c.llm.GenerateContentto generate a text completion.\n - Sanitization: Absent. No escaping or validation of the input string is performed.\n- [EXTERNAL_DOWNLOADS] (LOW): The code examples reference third-party Go modules from non-standard repositories.\n
- Evidence: Import of
github.com/leeif/langchaingoandgithub.com/futurxlab/golanggraph. These are not from the trusted organization list but appear as educational references in this context.\n- [SAFE] (INFO): Malicious URL Alert Analysis.\n - The scanner alert for
llms.Meis a false positive caused by the automated tool misparsing the Go data typellms.MessageContentas a domain name. No actual references to malicious domains were found in the source code.
Recommendations
- Contains 2 malicious URL(s) - DO NOT USE
Audit Metadata