app-store-publisher-leads
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to add a Model Context Protocol (MCP) server using the command
claude mcp add --transport http manypi https://mcp.manypi.com/mcp -s user. This connects the agent to an external service hosted by the vendor to perform lead generation tasks. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external app store marketplaces and plugin directories. This creates a surface for indirect prompt injection if listing data (such as app descriptions or reviews) contains malicious instructions for the agent. The skill lacks explicit boundary markers or sanitization steps for this external content.
- Ingestion points: Data fetched from app store listings and platform marketplaces (SKILL.md).
- Boundary markers: None explicitly defined in the prompt templates.
- Capability inventory: The skill uses an MCP tool to query and retrieve publisher data.
- Sanitization: No explicit sanitization or filtering of external data is defined in the instructions.
Audit Metadata