oodle-discovery

Pass

Audited by Gen Agent Trust Hub on Jul 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill offers to install the uv Python package manager using its official installation script from astral.sh if the tool is missing. This is a well-known, high-reputation service, and the download is part of the intended environment setup.
  • [COMMAND_EXECUTION]: Collector scripts (e.g., collectors/k8s/collect.py, collectors/gcp/collect.py) utilize subprocess.run and subprocess.Popen to interface with system binaries including kubectl, gcloud, and aws. These commands are hardcoded and used exclusively for read-only metadata discovery as described in the skill's core rules.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from cluster configurations and cloud metadata (e.g., pod names, CRDs). It effectively mitigates indirect prompt injection risks by instructing the agent to treat this data as unverified and by performing HTML escaping in report/template.py before rendering the final report.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 22, 2026, 12:59 AM
Security Audit — agent-trust-hub — oodle-discovery