Skills
Navigate
skills/grafana/gcx/diagnose-entity-graph/Gen Agent Trust Hub

diagnose-entity-graph

Pass

Audited by Gen Agent Trust Hub on Jul 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute several shell commands using the gcx CLI tool, such as gcx kg status, gcx kg health, gcx metrics query, and gcx kg cypher, to perform system diagnostics.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) due to its data ingestion flow. 1. Ingestion points: The agent reads and interprets output from gcx kg diagnose, gcx metrics query, and Cypher queries. 2. Boundary markers: No explicit delimiters or instructions are used to isolate or ignore instructions within the ingested data. 3. Capability inventory: The agent has the capability to execute shell commands via the gcx tool. 4. Sanitization: There is no evidence of sanitization or filtering of the content retrieved from external sources before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 28, 2026, 06:07 PM
Security Audit — agent-trust-hub — diagnose-entity-graph