Skills
skills/cockroachlabs/cockroachdb-skills/configuring-log-export/Gen Agent Trust Hub

configuring-log-export

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill exclusively utilizes official vendor tools (ccloud CLI) and well-known cloud provider CLIs (aws, gcloud) to perform configuration tasks.- [SAFE]: Credentials, such as Datadog API keys and AWS IAM Role ARNs, are handled using clear placeholders, and the skill provides guidance on setting up least-privileged IAM roles.- [PROMPT_INJECTION]: An indirect prompt injection surface exists as the skill ingests output from CLI tools and SQL queries to verify configuration status.
  • Ingestion points: ccloud cluster info <cluster-name> -o json (SKILL.md) and SHOW CLUSTER SETTING (SKILL.md).
  • Boundary markers: None used for tool output interpolation.
  • Capability inventory: Shell command execution via ccloud, aws, and gcloud (SKILL.md).
  • Sanitization: No explicit sanitization or validation of ingested output is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 10:27 PM