skills/grafana/gcx/debug-with-grafana/Gen Agent Trust Hub

debug-with-grafana

Pass

Audited by Gen Agent Trust Hub on Jun 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on the gcx command-line interface for all data retrieval operations. It also uses python3 -c as a helper to parse JSON output from the CLI when extracting specific fields like datasource UIDs.
  • [PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks (Category 8) because it ingests untrusted data from external observability sources (Loki logs and Tempo traces).
  • Ingestion points: Untrusted data enters the agent's context through gcx logs query (Step 5) and gcx traces query (Step 5b).
  • Boundary markers: The skill does not explicitly instruct the agent to use delimiters or ignore embedded instructions within the logs or traces, though it provides a structured summary format in Step 7.
  • Capability inventory: The skill has the capability to execute shell commands via gcx and perform filesystem writes via gcx dashboards snapshot (Step 6).
  • Sanitization: No explicit sanitization or filtering of the log/trace content is performed before the agent processes it for the final summary.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 30, 2026, 02:04 PM
Security Audit — agent-trust-hub — debug-with-grafana