rig
Warn
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSCREDENTIALS_UNSAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill performs extensive shell command execution to analyze the environment and apply configurations, including global installation of tools via
npm install -g lefthook. - [EXTERNAL_DOWNLOADS]: Automatically triggers downloads and installations through various package managers (npm, yarn, pnpm, bun) based on detected project types.
- [CREDENTIALS_UNSAFE]: Specifically targets and retrieves sensitive Azure DevOps credentials from environment variables (
AZURE_DEVOPS_EXT_PATorAZDO_PAT) for authentication purposes. - [DATA_EXFILTRATION]: Transmits Base64-encoded credentials via
curlto endpoints derived from the repository's remote URL, which could lead to credential exposure if a malicious remote is configured. - [PROMPT_INJECTION]: Uses high-priority instructions to force the agent to reproduce specific ASCII art and taglines ("CRITICAL: Reproduce the banner EXACTLY"), which is a technique used to override standard agent output behaviors.
Audit Metadata