skills/vertz-dev/claude-code/backlog/Gen Agent Trust Hub

backlog

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • Indirect Prompt Injection (LOW): The skill ingests untrusted data from user input and GitHub issue descriptions which could theoretically contain instructions intended to influence the agent.
  • Ingestion points: User-provided <description> in the /backlog add command and output from gh issue list.
  • Boundary markers: Absent; the skill does not wrap interpolated data in specific delimiters or safety instructions.
  • Capability inventory: Subprocess execution of gh CLI commands for issue creation and management.
  • Sanitization: Absent; input is passed directly to command-line arguments.
  • Command Execution (SAFE): The skill uses gh issue commands to perform its primary function. These are standard operations for GitHub repository management and do not involve unauthorized privilege escalation or dangerous shell features.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:44 PM