Pod CrashLoop Runbook

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documentation provides installation instructions that involve downloading and executing code from external sources using tools like npx (npx skills add agentskillexchange/skills) and clawhub (clawhub install pod-crashloop-runbook).
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it is designed to ingest and process potentially untrusted data from a Kubernetes environment.
  • Ingestion points: Cluster logs and events retrieved via kubectl and the Kubernetes API server (SKILL.md).
  • Boundary markers: There are no specified boundary markers or instructions to treat ingested data as untrusted in the skill's instructions.
  • Capability inventory: The skill interfaces with kubectl to manage cluster resources like pods and deployments (SKILL.md).
  • Sanitization: The skill lacks documented sanitization or filtering for the external data it processes.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 03:36 AM