prospect
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a legitimate business workflow for prospecting sales leads. It uses standard Model Context Protocol (MCP) tools for the Apollo platform and contains no malicious command execution, data exfiltration, or obfuscation.
- [SAFE]: Responsible resource management is observed through the inclusion of credit consumption warnings to the user before the agent performs high-cost enrichment operations.
- [PROMPT_INJECTION]: The skill processes user input via the
$ARGUMENTSvariable to define the Ideal Customer Profile (ICP). While the input is untrusted, the risk of indirect prompt injection is low because the agent is instructed to parse the text into structured filters for search tools rather than executing the raw text as a command. Boundary markers are absent, but the specific tool-calling intent limits the potential impact.
Audit Metadata