job-board-hiring-signals
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches and installs a Model Context Protocol (MCP) server from https://mcp.manypi.com/mcp. This is a vendor-owned resource originating from the skill author and is used to provide the skill's lead generation capabilities.
- [COMMAND_EXECUTION]: The documentation provides a shell command (
claude mcp add) for the user to register the ManyPI MCP server. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze text from external sources such as job boards and company career pages, which creates a potential surface for indirect prompt injection. 1. Ingestion points: Public job boards, company careers pages, and ATS-hosted listings. 2. Boundary markers: The skill does not include specific boundary markers or instructions for the agent to ignore embedded commands in the source data. 3. Capability inventory: Uses the ManyPI MCP tool for data processing and network operations. 4. Sanitization: No explicit content sanitization or filtering logic is defined for the external data.
Audit Metadata