gcp-cost-optimizer

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [Data Exposure & Exfiltration] (SAFE): The skill accesses sensitive GCP billing information through gcloud and bq commands. This is the primary intended purpose of the skill and no unauthorized exfiltration patterns were detected.
  • [Command Execution] (SAFE): The instructions use standard cloud management CLI tools (gcloud, bq). No evidence of privilege escalation, such as sudo, or suspicious system modifications was found.
  • [Indirect Prompt Injection] (SAFE): The skill defines a surface for processing untrusted data (Ingestion points: bq query output in SKILL.md; Boundary markers: Absent; Capability inventory: gcloud recommender calls in SKILL.md; Sanitization: Absent). However, this risk is mitigated by the fact that the skill is used for its primary intended purpose of cost analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:26 PM