check-ci

Pass

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill fetches and summarizes CI logs from external sources, creating a vulnerability where malicious log content could influence agent behavior. 1. Ingestion points: CI log output from gh or gt commands. 2. Boundary markers: Absent in instructions. 3. Capability inventory: Local command execution via gh and gt. 4. Sanitization: No sanitization or filtering of log content is specified.
  • [Command Execution] (SAFE): The skill utilizes gh (GitHub CLI) and gt (Graphite CLI) to retrieve status information. This is standard behavior for the tool's primary purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 18, 2026, 12:29 AM