debug-build

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted external data from OpenShift build logs and resource configurations, creating a surface for indirect prompt injection.
  • Ingestion points: Data is retrieved using pod_logs and resources_get from the cluster environment as described in SKILL.md steps 2, 3, and 4.
  • Boundary markers: The skill does not use explicit delimiters or instructions to the agent to disregard instructions potentially embedded in logs or metadata.
  • Capability inventory: The skill possesses the capability to list and read Kubernetes resources and logs via the MCP.
  • Sanitization: Log content and configuration data are not sanitized or filtered before being processed by the model for diagnosis.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 04:04 PM