renovate-rebase

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill instructions explicitly direct the AI agent to bypass human confirmation prompts ("Run this skill straight through to the end without asking the user anything"), which reduces user oversight during autonomous operation.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes external GitHub issue bodies that could contain malicious instructions.\n
  • Ingestion points: The tick_dashboard.py script retrieves issue content via gh issue view.\n
  • Boundary markers: No delimiters or explicit instructions are provided to the agent to disregard instructions embedded within the issue content.\n
  • Capability inventory: The skill can execute shell commands via the GitHub CLI and modify issue content.\n
  • Sanitization: No specific sanitization or filtering is applied to the issue body content before the agent processes the script's output or when the script re-uploads the modified body.\n- [COMMAND_EXECUTION]: The skill uses a Python script to execute the GitHub CLI tool (gh) using the subprocess module. The implementation uses list-based arguments, which is a recommended security practice to prevent shell injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 06:55 PM
Security Audit — agent-trust-hub — renovate-rebase