Skills
Navigate
skills/new-career-begin/queryweaver/prometheus-configuration/Gen Agent Trust Hub

prometheus-configuration

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources that could be influenced by an attacker.
  • Ingestion points: Kubernetes pod and service annotations (e.g., prometheus.io/scrape), external metrics endpoints (/metrics), and file-based service discovery targets.
  • Boundary markers: None observed in the prompt interpolation.
  • Capability inventory: Executes helm for installation, promtool for validation, and curl for status checks.
  • Sanitization: No specific sanitization or validation of the content retrieved from external metrics endpoints or Kubernetes annotations before being processed.
  • [EXTERNAL_DOWNLOADS]: Fetches Helm charts from the Prometheus Community repository.
  • Evidence: helm repo add prometheus-community https://prometheus-community.github.io/helm-charts in SKILL.md.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 03:05 PM
Security Audit — agent-trust-hub — prometheus-configuration