log-posthog-issues

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill possesses a surface for indirect prompt injection by processing external audit findings into shell commands.
  • Ingestion points: Data from the /check-posthog command output (variables like $TITLE, $DESCRIPTION, $IMPACT).
  • Boundary markers: None. Data is interpolated directly into shell heredocs and command-line arguments.
  • Capability inventory: Execution of gh (GitHub CLI) commands to create issues and labels.
  • Sanitization: No escaping or validation is performed on the input variables before they are executed in the shell.
  • [Command Execution] (LOW): The skill dynamically assembles and runs shell commands (gh issue create). This is the primary functional purpose of the skill and follows a known template, but it relies on the safety of the input data provided by the audit process.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:39 PM