funding-news-signals
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides a shell command to add an MCP (Model Context Protocol) server:
claude mcp add --transport http manypi https://mcp.manypi.com/mcp -s user. This connects the agent to a remote tool hosted on the vendor's domain (manypi.com).- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data from various web sources (funding announcements, LinkedIn changes, press releases). - Ingestion points: External websites, news articles, LinkedIn profiles, and changelogs are processed by the agent.
- Boundary markers: None explicitly defined in the instructions for the agent to separate data from instructions.
- Capability inventory: The skill suggests using the ManyPI tool to read live sources, implying network read capabilities.
- Sanitization: No specific sanitization or filtering instructions are provided for the fetched external content.
Audit Metadata