ax-extract-workflow

Pass

Audited by Gen Agent Trust Hub on Aug 4, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: Orchestrates the local ax CLI tool to perform searches and inspect session data using subcommands like ax recall and ax sessions show. These are used as read-only inspection operations to gather evidence for workflow reconstruction.
  • [DATA_EXFILTRATION]: The skill instructs the agent to access local session logs and git commit history which may contain sensitive information. However, it explicitly mitigates risk by instructing the agent to redact secrets, tokens, and private data, and warns against uploading this data to external services.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 4, 2026, 08:34 PM
Security Audit — agent-trust-hub — ax-extract-workflow