agent-app-store
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill operates as a marketplace manager, ingesting external data that could potentially contain malicious instructions intended to influence the agent's behavior.
- Ingestion points: The skill retrieves external data through search results in
mcp__flow-nexus__app_searchand analytics data inmcp__flow-nexus__app_analytics. - Boundary markers: The skill does not define specific delimiters or instructions to the agent to disregard embedded commands within the marketplace content it processes.
- Capability inventory: The agent has significant capabilities including publishing new applications via
mcp__flow-nexus__app_store_publish_appand deploying templates with configuration variables viamcp__flow-nexus__template_deploy. - Sanitization: There are no explicit content validation or sanitization requirements mentioned in the instructions to prevent the execution of instructions found within app descriptions or search results.
Audit Metadata