conference-exhibitor-leads
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides a command to add an MCP (Model Context Protocol) tool from
https://mcp.manypi.com/mcp. This URL belongs to the skill's author domain and is used to extend the agent's capabilities with lead generation functionality. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from external sources such as exhibitor directories, speaker pages, and event floor plans. This creates a surface for indirect prompt injection if these third-party sources contain malicious instructions.
- Ingestion points: External URLs for event directories, sponsor pages, and agenda pages are processed to extract lead data.
- Boundary markers: The instructions do not specify the use of delimiters or boundary markers to isolate external content from the system prompt.
- Capability inventory: The skill utilizes an MCP tool (
manypi) for data processing and lead generation tasks. - Sanitization: There are no explicit instructions for sanitizing or filtering instructions embedded within the ingested conference data.
Audit Metadata