synth-investigate-check
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute gcx (Grafana CLI) commands to retrieve check configurations, status, timelines, and to query metrics via PromQL. This is the primary mechanism for the skill's functionality and is consistent with its stated purpose.
- [INDIRECT_PROMPT_INJECTION]: The skill demonstrates an attack surface for indirect prompt injection by interpolating user-provided inputs, such as check IDs and job names, directly into shell commands. * Ingestion points: User-provided strings for IDs and names are used in shell commands. * Boundary markers: The instructions do not specify boundary markers or delimiters for these inputs. * Capability inventory: The skill possesses shell execution capabilities via the Bash tool. * Sanitization: The skill lacks explicit sanitization logic for user-provided identifiers, relying on the agent's inherent safety guardrails.
Audit Metadata