account-based-marketing-leadgen
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill includes instructions to add a remote Model Context Protocol (MCP) server using the command
claude mcp add --transport http manypi https://mcp.manypi.com/mcp -s user. This external resource, hosted on the developer's domain, is intended to automate the research of target accounts and buying committees by accessing web data. - [INDIRECT_PROMPT_INJECTION]: The skill describes a process where the agent researches the live web for named individuals, their priorities, and public statements to build account briefs. This creates a vulnerability surface where malicious content on external websites could attempt to influence the agent's behavior.
- Ingestion points: Live web research conducted via the ManyPI MCP server as described in
SKILL.md. - Boundary markers: None identified in the skill instructions to delimit untrusted web data from the agent's core instructions.
- Capability inventory: The skill adds an MCP tool (
claude mcp add) with network transport capabilities to perform research and potentially communicate with external APIs. - Sanitization: There are no instructions provided for sanitizing or filtering the content retrieved from the web before it is processed by the agent.
Audit Metadata