ax-extract-workflow
Pass
Audited by Gen Agent Trust Hub on Aug 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions include executing shell commands using the
axCLI tool (e.g.,ax recall,ax sessions) to query local session metadata, commits, and logs. This is functional and restricted to local data access. - [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection. It ingests data from past agent sessions via
ax sessions show, which may include untrusted content or instructions from previous interactions. The skill lacks explicit boundary markers or sanitization instructions for this historical data, which could lead the agent to follow instructions embedded in the logs it is analyzing.
Audit Metadata