nav-pilot

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: Uses the GitHub CLI (gh) via the Bash tool to create issues. The skill explicitly instructs the agent to display the full command for user review before execution.
  • [EXTERNAL_DOWNLOADS]: Interacts with GitHub to create issues. This network operation targets a well-known service and is necessary for the skill's primary function of dispatching tasks to external workers.
  • [PROMPT_INJECTION]: The skill implements a 'Pre-flight Confirmation' checkpoint (Step 4). This safety mechanism requires explicit user approval ('Enter to dispatch') before the agent performs the outward-facing action, preventing autonomous execution of potentially harmful or incorrect commands.
  • [DATA_EXFILTRATION]: Reads task metadata and content from the .agent/ directory. This data is transferred to the user's configured GitHub repository. This behavior is consistent with the skill's stated purpose and uses established authentication via gh auth.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 03:53 PM
Security Audit — agent-trust-hub — nav-pilot