skills/synkraai/aios-core/aiox-devops/Gen Agent Trust Hub

aiox-devops

Warn

Audited by Gen Agent Trust Hub on Mar 22, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a Node.js script located at '.aiox-core/development/scripts/generate-greeting.js' as part of its activation protocol.
  • [PROMPT_INJECTION]: The skill dynamically loads agent instructions and persona definitions from local files ('.aiox-core/development/agents/devops.md' and '.aiox-core/constitution.md'). 1. Ingestion points: Reads instructions from files in the local '.aiox-core' directory. 2. Boundary markers: No delimiters or ignore-embedded-instruction warnings are present to isolate the loaded content. 3. Capability inventory: Significant privileges including shell command execution via Node.js and GitHub repository management (push, PR creation, CI/CD config). 4. Sanitization: No sanitization or validation of the loaded file content is implemented.
  • [COMMAND_EXECUTION]: Provides commands for high-privilege repository operations such as '*push', '*create-pr', '*configure-ci', and '*release' which can modify remote code and automation workflows.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 22, 2026, 03:39 PM
Security Audit — agent-trust-hub — aiox-devops