tam-from-verified-data
Pass
Audited by Gen Agent Trust Hub on Aug 23, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided inputs through $ARGUMENTS such as ICP definitions and target buyer descriptions. This constitutes a surface for indirect prompt injection if the inputs contain malicious instructions. However, the skill does not define any capabilities or tools (no file writing, network requests, or shell command execution) that could be leveraged by such an injection. The instruction set lacks explicit delimiters or instructions to sanitize these inputs.
- [EXTERNAL_DOWNLOADS]: The skill contains a reference link to Lusha's official website for documentation purposes. As Lusha is a well-known service, this reference is informative and does not involve automated downloads or execution of remote code.
Audit Metadata