gather-arcgis-application-requirements
Pass
Audited by Gen Agent Trust Hub on Nov 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to inspect existing project configurations and conversation history to establish application requirements. This creates a surface for indirect prompt injection, as malicious instructions embedded within a workspace's configuration files or documentation could attempt to influence the agent's architectural planning or technology selection.
- Ingestion points: Conversation history and project-level configuration files as specified in the 'Review context first' execution rule.
- Boundary markers: None; there are no explicit instructions to treat external project data as untrusted or to use specific delimiters.
- Capability inventory: The skill is a planning and routing tool; it does not contain capabilities for file modification, command execution, or network exfiltration.
- Sanitization: No sanitization or validation procedures are defined for the project context data ingested during the requirements phase.
- [EXTERNAL_DOWNLOADS]: The skill references and utilizes an external Model Context Protocol (MCP) server located at
https://developers-mcp.arcgis.com/mcpto retrieve official developer documentation and verify product capabilities.
Audit Metadata