gate-info-marketoverview
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes real-time news and event data from external sources via the news_events_get_latest_events tool. * Ingestion points: news_events_get_latest_events tool output used in SKILL.md. * Boundary markers: The report template lacks explicit delimiters or instructions for the agent to ignore potentially malicious directions embedded within event summaries retrieved from external sources. * Capability inventory: The skill utilizes local shell execution (Bash and PowerShell) for maintenance and update tasks, as well as intent-based routing. * Sanitization: There is no evidence of input validation or sanitization for the text data retrieved from external news feeds.
- [EXTERNAL_DOWNLOADS]: The skill contains update scripts (update-skill.sh and update-skill.ps1) that fetch new versions of the skill from the official Gate GitHub repository (github.com/gate/gate-skills).
- [COMMAND_EXECUTION]: The skill utilizes local shell and PowerShell commands to perform environment checks, routing logic between skill versions, and to facilitate the self-update process from vendor-controlled infrastructure.
Audit Metadata