slo-check-status
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
gcxCLI commands through Bash to interact with Grafana services. These commands are used to list SLO definitions, check health status, and retrieve historical data for graphing. This is consistent with the skill's primary purpose and uses a vendor-provided tool. - [INDIRECT_PROMPT_INJECTION]: The skill ingests SLO metadata (such as names and status strings) from an external Grafana instance. While this presents an attack surface where malicious data could influence agent behavior, the risk is minimal as the skill primarily formats this data into structured tables or graphs.
- Ingestion points: Data enters the context via
gcxcommand outputs inSKILL.md. - Boundary markers: Absent; the skill relies on standard command output formatting.
- Capability inventory: The skill utilizes Bash command execution through the
gcxtool as defined inSKILL.md. - Sanitization: Absent; external content from the monitoring tool is displayed directly to the user.
Audit Metadata