Skills
skills/render-oss/skills/render-monitor/Gen Agent Trust Hub

render-monitor

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • Indirect Prompt Injection (HIGH): The skill reads untrusted service logs while having access to high-privilege tools. 1. Ingestion points: list_logs in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: query_render_postgres (SQL) and render ssh (Shell access). 4. Sanitization: Absent.
  • Command Execution (HIGH): Direct access to render ssh and query_render_postgres provides powerful primitives for system and database manipulation that can be easily abused if the agent is manipulated.
  • External Downloads (MEDIUM): The skill instructs the configuration of an external MCP server from https://mcp.render.com/mcp, which is not a pre-approved trusted source according to the provided security list.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 05:44 AM