voicemail-drop-strategy
Pass
Audited by Gen Agent Trust Hub on Sep 8, 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 tool is utilized to research target accounts to improve the specificity of voicemail messages. The source is the official domain associated with the skill author.
- [INDIRECT_PROMPT_INJECTION]: The skill describes a workflow where external data retrieved from a research tool is used to generate personalized voicemail content.
- Ingestion points: Account-specific details retrieved through the ManyPI MCP tool into the agent's context.
- Boundary markers: The instructions do not specify any delimiters or warnings to ignore instructions that might be embedded in the retrieved account data.
- Capability inventory: The skill uses the ingested data to formulate text for voicemail scripts.
- Sanitization: No specific validation or filtering of the external account data is defined in the instructions.
Audit Metadata