gke-ai-troubleshooting-tpu-vbar-oom

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input via multiple variables such as {project_id}, {cluster_name}, {node_name}, {workload_name}, and {namespace} which are directly interpolated into Cloud Logging (LQL) query templates in SKILL.md.
  • Ingestion points: Variable definitions in SKILL.md (Step 0) used across Steps 1, 2, and 3.
  • Boundary markers: Absent; there are no delimiters or instructions provided to the agent to treat these specific values as data rather than instructions if they contain malicious payloads.
  • Capability inventory: The skill uses the query_logs tool and executes kubectl commands.
  • Sanitization: Absent; the instructions do not specify any validation or escaping of the user-provided strings before they are used to construct queries.
  • [COMMAND_EXECUTION]: The skill provides and encourages the execution of a kubectl command in SKILL.md (Step 3) that performs a cluster-wide scan using the -A flag to list all pod names and container images across every namespace. This exposes broad workload metadata to the agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 05:41 AM
Security Audit — agent-trust-hub — gke-ai-troubleshooting-tpu-vbar-oom