Skills
Navigate
skills/firetiger-oss/cursor-plugin/firetiger-monitor-deploy/Gen Agent Trust Hub

firetiger-monitor-deploy

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves processing untrusted data from external sources, which is a common surface for indirect injection.
  • Ingestion points: Analysis of GitHub PR diffs via the monitor_pr tool and processing of GitHub comments (e.g., @firetiger mentions).
  • Boundary markers: The instructions do not explicitly specify delimiters or boundary markers for the AI when processing PR content, though this is typical for monitoring agents.
  • Capability inventory: The skill utilizes MCP tools to manage agents and sessions (send_agent_message, read_agent_messages), and provides examples for using the gh CLI and curl for deployment registration.
  • Sanitization: Data sanitization is handled by the backend Firetiger monitoring service rather than within the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 12:34 AM