prometheus-addxai

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill processes external monitoring data from the Prometheus API, which serves as an ingestion point for untrusted data that could contain embedded instructions intended to influence the agent.
  • Ingestion points: Output from Prometheus API queries (e.g., node, kafka, and container metrics) processed in SKILL.md examples.
  • Boundary markers: Absent; there are no instructions to the agent to treat API output as untrusted data or to ignore instructions within it.
  • Capability inventory: Network access via curl and data manipulation via jq.
  • Sanitization: Absent.
  • [COMMAND_EXECUTION]: The skill provides templates and examples for executing shell commands including curl, jq, and date to interact with Prometheus and process its output.
  • [EXTERNAL_DOWNLOADS]: The skill performs network operations using curl to fetch data from an external Prometheus server defined by the PROMETHEUS_URL environment variable.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 05:51 PM
Security Audit — agent-trust-hub — prometheus-addxai